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

    Neuronpedia

    INDEX
    Explanations

    From

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Digest
    -0.06
    Pt
    -0.06
     кас
    -0.06
     Bolshevik
    -0.06
    Symbol
    -0.06
     Pall
    -0.06
     Oliver
    -0.06
    ServletResponse
    -0.06
    Magic
    -0.06
     Bobby
    -0.06
    POSITIVE LOGITS
    ),
    0.07
    ิ์
    0.06
     области
    0.06
     ();↵
    0.06
    ired
    0.06
    Directed
    0.06
    LocalStorage
    0.06
    "
↵
    0.06
     :|
    0.06
    vní
    0.06
    Act Density 0.222%

    No Known Activations