Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate conditions or states related to certainty or necessity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions and determiners in multiple languages

    np_acts-logits-general · gemini-2.0-flash

    multi-lingual phrases and code constructs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ModelExpression
    -0.63
    setVerticalGroup
    -0.58
     iodide
    -0.54
    ethene
    -0.52
     pyridine
    -0.52
     Guadeloupe
    -0.52
     Mauritania
    -0.51
     osób
    -0.51
     bromine
    -0.51
     bromide
    -0.51
    POSITIVE LOGITS
    WebElementEntity
    0.57
    Bereich
    0.54
    thof
    0.54
    urtstag
    0.53
     anyway
    0.53
     she
    0.52
    lasser
    0.52
    Personensuche
    0.51
     समीक्षक
    0.50
    ChildScrollView
    0.49
    Act Density 0.033%

    No Known Activations