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

    Neuronpedia

    INDEX
    Explanations

    Arctic/Antarctic regions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     incorporating
    -0.08
    <Image
    -0.07
     stor
    -0.07
     historic
    -0.07
    古镇
    -0.07
    支撑
    -0.07
     Wo
    -0.07
    sharing
    -0.06
    鉴
    -0.06
     Agr
    -0.06
    POSITIVE LOGITS
     uważ
    0.08
     duż
    0.08
    ﮥ
    0.07
    ملاب
    0.07
    近距离
    0.07
    blockquote
    0.07
    眉头
    0.07
     Rebel
    0.07
     Amateur
    0.07
     USS
    0.07
    Act Density 0.026%

    No Known Activations