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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Paras
    -0.07
     Jon
    -0.07
    badge
    -0.06
     возникнов
    -0.06
    отв
    -0.06
     Belmont
    -0.06
     My
    -0.06
    emen
    -0.06
     Modern
    -0.06
    ponge
    -0.06
    POSITIVE LOGITS
    の中
    0.07
    ibr
    0.07
     thẳng
    0.07
     필
    0.06
     �
    0.06
    acco
    0.06
    用户
    0.06
    .jpg
    0.06
    แสง
    0.06
     sidelined
    0.06
    Act Density 0.009%

    No Known Activations