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

    Neuronpedia

    INDEX
    Explanations

    references to "appearance" or related visual descriptors

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

    appearance settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    pecabe
    -0.67
     NSCoder
    -0.60
    thschild
    -0.59
     Inscrivez
    -0.59
    ckså
    -0.59
    ImageContext
    -0.58
    endaft
    -0.57
     Púb
    -0.57
     Cientí
    -0.56
     hidrá
    -0.55
    POSITIVE LOGITS
    enance
    0.64
    ment
    0.59
    itation
    0.59
    cination
    0.58
    rance
    0.58
    ARANCE
    0.56
    rence
    0.56
    pearance
    0.56
     assistance
    0.55
    membrance
    0.54
    Act Density 0.010%

    No Known Activations