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

    Neuronpedia

    INDEX
    Explanations

    access

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .dispose
    -0.08
     leží
    -0.07
    (*)(
    -0.06
     Вони
    -0.06
    爷
    -0.06
     Sequential
    -0.06
     Куб
    -0.06
     lvl
    -0.06
     zů
    -0.06
    particles
    -0.06
    POSITIVE LOGITS
    ida
    0.07
     competing
    0.06
    .documents
    0.06
    _identifier
    0.06
     amaç
    0.06
    nější
    0.06
     Mel
    0.06
    ım
    0.06
    asking
    0.05
     Porn
    0.05
    Act Density 0.004%

    No Known Activations