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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions and inequalities

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

    mathematical and programming symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    +#+
    -0.53
    EndGlobalSection
    -0.52
    matchCondition
    -0.51
     dispensed
    -0.51
    ########.
    -0.50
     onData
    -0.47
    LEncoder
    -0.47
     FetchType
    -0.46
    テンツ
    -0.46
    Datuak
    -0.45
    POSITIVE LOGITS
    parsedMessage
    0.58
    aarrggbb
    0.42
     rozdí
    0.38
     penderita
    0.38
     spéciaux
    0.38
     différence
    0.37
     belki
    0.37
    衅
    0.37
    Revenir
    0.36
     différences
    0.36
    Act Density 0.262%

    No Known Activations