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

    Neuronpedia

    INDEX
    Explanations

    instances of whitespace or empty lines in the text

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

    parenthesized names and terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TacToe
    -0.40
    endregion
    -0.39
    chery
    -0.39
     Breed
    -0.38
    eeeee
    -0.36
    brio
    -0.36
    Be
    -0.36
    betreuung
    -0.35
     tutaj
    -0.35
     melee
    -0.34
    POSITIVE LOGITS
    　　
    0.70
    SBATCH
    0.67
    Décès
    0.62
     　
    0.59
    　
    0.57
    　　　
    0.55
     　　
    0.53
    Personendaten
    0.53
    )　
    0.52
     ModelExpression
    0.52
    Act Density 0.044%

    No Known Activations