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
    그래
    -0.07
    _PIPELINE
    -0.07
    .geo
    -0.07
    (render
    -0.07
    PRINT
    -0.07
     Homer
    -0.06
    _documents
    -0.06
    /event
    -0.06
    INNER
    -0.06
    .keep
    -0.06
    POSITIVE LOGITS
    工商联
    0.08
    лся
    0.08
     crossed
    0.06
     dục
    0.06
     comparable
    0.06
    attice
    0.06
     opposing
    0.06
    本地
    0.06
    做起
    0.06
    лись
    0.06
    Act Density 0.004%

    No Known Activations