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

    Neuronpedia

    INDEX
    Explanations

    happened

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    됨
    -0.07
    _ng
    -0.06
     Пів
    -0.06
     tran
    -0.06
    riends
    -0.06
    hashed
    -0.06
    .googleapis
    -0.06
     jealous
    -0.06
    زيز
    -0.06
     فس
    -0.06
    POSITIVE LOGITS
    HO
    0.07
    har
    0.06
    νια
    0.06
    mination
    0.06
    měr
    0.06
    uffer
    0.06
    ADOS
    0.06
    MER
    0.06
     HE
    0.06
     Gal
    0.06
    Act Density 0.000%

    No Known Activations