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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     volta
    -0.09
     phạm
    -0.08
     जिसका
    -0.08
    icii
    -0.08
     ++)
    -0.08
     sabotage
    -0.08
     जिसकी
    -0.08
    ikov
    -0.08
    ímica
    -0.08
    aderno
    -0.08
    POSITIVE LOGITS
    (filters
    0.09
    /filter
    0.09
     отображ
    0.08
    /list
    0.08
    (filtered
    0.08
    View
    0.08
    /search
    0.08
     filters
    0.08
     Darstellung
    0.08
    (properties
    0.08
    Act Density 0.018%

    No Known Activations