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

    Neuronpedia

    INDEX
    Explanations

    surprise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Μά
    -0.07
     sweets
    -0.07
     Draw
    -0.06
     Cz
    -0.06
    課
    -0.06
    _rank
    -0.06
    tempt
    -0.06
     Sv
    -0.06
    给
    -0.06
    烧
    -0.06
    POSITIVE LOGITS
     “
    0.06
     surprising
    0.06
    unter
    0.06
    findOrFail
    0.06
     generally
    0.06
     MSI
    0.06
     системи
    0.06
     backgrounds
    0.06
    rox
    0.06
    ickers
    0.06
    Act Density 0.007%

    No Known Activations