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

    Neuronpedia

    INDEX
    Explanations

    Programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     elo
    -0.07
     dado
    -0.07
     CLR
    -0.06
    Firefox
    -0.06
    ottie
    -0.06
    Hong
    -0.06
    cx
    -0.06
    Tro
    -0.06
     Hon
    -0.06
    poň
    -0.06
    POSITIVE LOGITS
    emark
    0.07
     हव
    0.07
     browse
    0.06
    vak
    0.06
    _depend
    0.06
    .uni
    0.06
    keh
    0.06
     ویکی
    0.06
     LOOK
    0.06
     noveller
    0.06
    Act Density 0.014%

    No Known Activations