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

    Neuronpedia

    INDEX
    Explanations

    files

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Gst
    -0.07
    òa
    -0.07
     müd
    -0.06
    après
    -0.06
    준
    -0.06
     attorney
    -0.06
    角度看
    -0.06
    弘扬
    -0.06
     พ
    -0.06
     nuest
    -0.06
    POSITIVE LOGITS
    Interface
    0.08
    .categories
    0.07
    .US
    0.07
    所在
    0.07
     nieruch
    0.07
     folds
    0.07
    $")↵
    0.07
    _CHARACTER
    0.07
    aturated
    0.07
    �
    0.07
    Act Density 0.001%

    No Known Activations