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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _sym
    -0.07
     bride
    -0.07
    (||
    -0.06
    žila
    -0.06
     wear
    -0.06
    (pr
    -0.06
     tip
    -0.06
    .Simple
    -0.06
    /tty
    -0.06
     tty
    -0.06
    POSITIVE LOGITS
    放在
    0.07
     poj
    0.06
    argin
    0.06
     meddling
    0.06
     professionnel
    0.06
    клад
    0.06
    ถาม
    0.06
    ulations
    0.06
     категор
    0.06
    CDC
    0.06
    Act Density 0.153%

    No Known Activations