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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    summary
    -0.07
     empower
    -0.06
    _supply
    -0.06
    ners
    -0.06
    _optimizer
    -0.06
    /or
    -0.06
    client
    -0.06
     Visibility
    -0.06
    crawler
    -0.06
    ataloader
    -0.06
    POSITIVE LOGITS
     هزار
    0.07
     Graham
    0.06
     Boh
    0.06
    750
    0.06
    460
    0.06
     yog
    0.06
     minValue
    0.06
    iê
    0.06
     Exception
    0.06
     Weld
    0.06
    Act Density 0.120%

    No Known Activations