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

    Neuronpedia

    INDEX
    Explanations

    expedition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    غان
    -0.07
     Maxwell
    -0.07
    ethoven
    -0.07
    aeda
    -0.07
    itic
    -0.07
     پزش
    -0.06
    ucle
    -0.06
     burada
    -0.06
    щи
    -0.06
    (cols
    -0.06
    POSITIVE LOGITS
     nah
    0.06
     inaugural
    0.06
     drawable
    0.06
     passive
    0.06
     closets
    0.06
    (EIF
    0.06
     раст
    0.06
    ————————————————
    0.06
    {!!
    0.06
    こん
    0.05
    Act Density 0.008%

    No Known Activations