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

    Neuronpedia

    INDEX
    Explanations

    represented

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mean
    -0.07
    boss
    -0.07
    Za
    -0.07
    mean
    -0.06
    割
    -0.06
    -validation
    -0.06
     unsettling
    -0.06
    führ
    -0.06
     Za
    -0.06
    -mean
    -0.06
    POSITIVE LOGITS
     represented
    0.09
     representation
    0.08
     字
    0.07
    ulates
    0.07
     imprimir
    0.06
     ओवर
    0.06
     thống
    0.06
     эк
    0.06
     fluent
    0.06
    )..
    0.06
    Act Density 0.011%

    No Known Activations