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

    Neuronpedia

    INDEX
    Explanations

    greater than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     officially
    -0.07
     Eb
    -0.07
     Daddy
    -0.06
     diversion
    -0.06
     swelling
    -0.06
     highest
    -0.06
     mi
    -0.06
    ierung
    -0.06
    _level
    -0.06
     Am
    -0.06
    POSITIVE LOGITS
    .argsort
    0.07
    TRY
    0.06
    ýn
    0.06
    google
    0.06
    larda
    0.06
    amp
    0.06
    show
    0.06
    oct
    0.06
    S
    0.06
    ぼ
    0.06
    Act Density 0.096%

    No Known Activations