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

    Neuronpedia

    INDEX
    Explanations

    Hello

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    もっと
    -0.07
    Wonder
    -0.07
     Ин
    -0.06
     çek
    -0.06
     hk
    -0.06
     importer
    -0.06
     Дж
    -0.06
     For
    -0.06
    LEEP
    -0.06
     internals
    -0.06
    POSITIVE LOGITS
    .lo
    0.07
    στηκε
    0.06
    .sel
    0.06
     Rapids
    0.06
    .decrypt
    0.06
    .Magic
    0.06
    _alt
    0.06
     bows
    0.06
     Sistem
    0.06
    .scale
    0.06
    Act Density 0.013%

    No Known Activations