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

    Neuronpedia

    INDEX
    Explanations

    words ending in "est", often used to indicate superlatives

    oai_token-act-pair · gemini-2.0-flash

    est

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     متعلقه
    -1.32
    IsContent
    -1.16
    IsMutable
    -1.15
    contentLoaded
    -1.14
    styleType
    -1.13
    Xna
    -1.13
     wireType
    -1.12
    aarrggbb
    -1.12
    sidemargin
    -1.10
    bootstrapcdn
    -1.09
    POSITIVE LOGITS
     
    0.97
     the
    0.81
    <strong>
    0.81
    <eos>
    0.72
    </em>
    0.69
     most
    0.62
    !
    0.62
    …
    0.61
     entire
    0.61
     “
    0.61
    Act Density 1.346%

    No Known Activations