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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     труд
    -0.07
     genital
    -0.07
     finances
    -0.07
    ulong
    -0.06
    ması
    -0.06
    #if
    -0.06
    ToFit
    -0.06
    .removeClass
    -0.06
    Azure
    -0.06
    ası
    -0.06
    POSITIVE LOGITS
     Homepage
    0.07
    <h
    0.07
    ，你
    0.06
    (true
    0.06
    (pc
    0.06
     провед
    0.06
    握
    0.06
    ，她
    0.06
    .Session
    0.06
     ee
    0.06
    Act Density 0.001%

    No Known Activations