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

    Neuronpedia

    INDEX
    Explanations

    Letter

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    remark
    -0.07
     Bloss
    -0.07
     thuận
    -0.06
     olm
    -0.06
     Ấn
    -0.06
     Hãy
    -0.06
     Arabs
    -0.06
    (Game
    -0.06
     هند
    -0.06
    /git
    -0.06
    POSITIVE LOGITS
    (dAtA
    0.07
     mutate
    0.06
     修改
    0.06
    _credit
    0.06
    过
    0.06
    .street
    0.06
     *@
    0.06
     jLabel
    0.06
    ickers
    0.06
     yoksa
    0.06
    Act Density 0.004%

    No Known Activations