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

    Neuronpedia

    INDEX
    Explanations

    Visual/flamboyant artists

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    偷
    -0.07
     computations
    -0.07
     hours
    -0.07
    tutorial
    -0.06
     SECOND
    -0.06
     curious
    -0.06
    -Sh
    -0.06
     Mostly
    -0.06
     ⇒
    -0.06
    (sent
    -0.06
    POSITIVE LOGITS
     Politics
    0.06
     Bulld
    0.06
    sti
    0.06
    mıştır
    0.06
    acute
    0.06
    玄
    0.06
     FX
    0.06
    ือก
    0.06
    DataExchange
    0.06
     altri
    0.06
    Act Density 0.038%

    No Known Activations