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

    Neuronpedia

    INDEX
    Explanations

    references to figures in the text

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

    Mentioning figures or diagrams

    np_acts-logits-general · gemini-2.0-flash

    figure citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     للمعارف
    -0.69
    曖昧さ回避
    -0.62
    évaluateur
    -0.59
    Искәрмәләр
    -0.56
    soever
    -0.56
    Biografi
    -0.55
    alogie
    -0.54
    Nuorodos
    -0.53
     matter
    -0.53
    ligo
    -0.52
    POSITIVE LOGITS
     Figure
    1.06
    Figure
    1.06
     figure
    0.99
    Figures
    0.90
     Figures
    0.89
     figures
    0.87
    figure
    0.86
    FIGURE
    0.79
     FIGURE
    0.75
     FIGURES
    0.74
    Act Density 0.213%

    No Known Activations