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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Back
    -0.07
    Writer
    -0.06
    Living
    -0.06
    SJ
    -0.06
    LEEP
    -0.06
    perial
    -0.06
    _printer
    -0.06
    contre
    -0.06
    NSInteger
    -0.06
    mart
    -0.06
    POSITIVE LOGITS
     rehears
    0.06
     Дата
    0.06
    udded
    0.06
     Beh
    0.06
     unins
    0.06
    .jasper
    0.06
     redund
    0.06
     miners
    0.06
     ayrı
    0.06
     thuê
    0.06
    Act Density 0.003%

    No Known Activations