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

    Neuronpedia

    INDEX
    Explanations

    corrupt

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     말했다
    -0.08
    本当
    -0.06
     ejemplo
    -0.06
    ToFront
    -0.06
     milit
    -0.06
    цієн
    -0.06
     Ис
    -0.06
     lavoro
    -0.06
     Fransız
    -0.06
     docking
    -0.06
    POSITIVE LOGITS
     corruption
    0.11
     Corruption
    0.09
    _legacy
    0.07
    cing
    0.07
    icers
    0.07
    enko
    0.07
     Components
    0.07
    ays
    0.07
    flt
    0.07
     disrupt
    0.06
    Act Density 0.004%

    No Known Activations