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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    hoot
    -0.06
     Took
    -0.06
     сход
    -0.06
     curs
    -0.06
    textInput
    -0.06
     katı
    -0.06
     Crash
    -0.06
     за
    -0.06
    етич
    -0.06
     profoundly
    -0.06
    POSITIVE LOGITS
    '''↵
    0.07
    ‬↵
    0.07
    พยาบาล
    0.07
    …↵
    0.06
     exhib
    0.06
    ）↵
    0.06
     dances
    0.06
    ]}↵
    0.06
    idency
    0.06
     memor
    0.06
    Act Density 0.000%

    No Known Activations