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

    Neuronpedia

    INDEX
    Explanations

    //

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Extent
    -0.07
     mužů
    -0.07
    grey
    -0.06
     hotline
    -0.06
     dấu
    -0.06
    تف
    -0.06
     及
    -0.06
     Cher
    -0.06
     Gig
    -0.06
     Ikea
    -0.06
    POSITIVE LOGITS
    =pd
    0.07
    _variance
    0.07
    Flow
    0.07
    rd
    0.07
    schemas
    0.06
    COM
    0.06
    inion
    0.06
     раніше
    0.06
    oundary
    0.06
     Wal
    0.06
    Act Density 0.003%

    No Known Activations