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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating definitive conclusions or necessary actions

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

    Followed by "to" and a verb

    np_acts-logits-general · gemini-2.0-flash

    singular conclusion or explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mxArray
    -0.56
    XmlEnum
    -0.47
     engraçadas
    -0.45
     abstrato
    -0.44
     Ferdin
    -0.43
    -0.43
    DataSetChanged
    -0.43
    Personensuche
    -0.41
    Inhalt
    -0.41
    Disliked
    -0.40
    POSITIVE LOGITS
    SequentialGroup
    0.65
    ScopeManager
    0.50
     conviene
    0.49
    只能
    0.42
    liflower
    0.41
    Portale
    0.41
    PYX
    0.40
    emptive
    0.40
    jspx
    0.40
    편
    0.39
    Act Density 0.424%

    No Known Activations