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

    Neuronpedia

    INDEX
    Explanations

    illegal activities

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ования
    -0.07
    жения
    -0.06
     =",
    -0.06
     =====
    -0.06
    966
    -0.06
     obdob
    -0.06
    렴
    -0.06
    _Cell
    -0.06
    PropertyValue
    -0.06
    itt
    -0.06
    POSITIVE LOGITS
     laundering
    0.17
     launder
    0.12
     Audrey
    0.09
     slander
    0.08
     Lauderdale
    0.08
     Saunders
    0.08
    .blit
    0.07
    UNDER
    0.07
     casually
    0.07
    Layers
    0.07
    Act Density 0.010%

    No Known Activations