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

    Neuronpedia

    INDEX
    Explanations

    common words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Everybody
    -0.08
    urpose
    -0.07
     Leh
    -0.07
    langle
    -0.07
    řaz
    -0.07
    Qualifier
    -0.07
    _DAY
    -0.07
    _buffer
    -0.06
    .Filters
    -0.06
     الاح
    -0.06
    POSITIVE LOGITS
     evenly
    0.08
     مشارکت
    0.07
    xp
    0.06
     topology
    0.06
     belg
    0.06
     treff
    0.06
    tring
    0.06
     Tow
    0.06
    orea
    0.06
    van
    0.05
    Act Density 0.001%

    No Known Activations