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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     VERY
    -0.08
    -mask
    -0.07
     trends
    -0.07
    绩
    -0.06
    ariant
    -0.06
    ToUpdate
    -0.06
    cházet
    -0.06
     hơn
    -0.06
    した
    -0.06
    APS
    -0.06
    POSITIVE LOGITS
     scrutin
    0.07
    UTF
    0.06
     इन
    0.06
     Denis
    0.06
     Responsive
    0.06
    _transport
    0.06
     Bunu
    0.06
    .Fill
    0.06
     obe
    0.06
     ekran
    0.06
    Act Density 0.026%

    No Known Activations