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

    Neuronpedia

    INDEX
    Explanations

    Performances

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Martha
    -0.07
    Daily
    -0.07
    225
    -0.06
     Appliances
    -0.06
    가를
    -0.06
    参加
    -0.06
    ाहर
    -0.06
     ltd
    -0.06
    158
    -0.06
    anka
    -0.06
    POSITIVE LOGITS
     för
    0.06
    -black
    0.06
    老
    0.06
    uddled
    0.06
     superclass
    0.06
    enn
    0.06
    (parameter
    0.06
     Záp
    0.06
    milliseconds
    0.06
    spec
    0.06
    Act Density 0.045%

    No Known Activations