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

    Neuronpedia

    INDEX
    Explanations

    Service

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     svým
    -0.07
    ław
    -0.06
    говор
    -0.06
    orted
    -0.06
    ladık
    -0.06
    criptive
    -0.06
     Assass
    -0.06
    Letters
    -0.06
     vlád
    -0.06
    sil
    -0.06
    POSITIVE LOGITS
     impro
    0.06
    菜
    0.06
     Ingen
    0.06
     court
    0.06
    _DELETE
    0.06
    AT
    0.06
     lig
    0.06
    .decorators
    0.06
     ta
    0.06
     Org
    0.06
    Act Density 0.000%

    No Known Activations