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

    Neuronpedia

    INDEX
    Explanations

    columns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    When
    -0.07
    ₂
    -0.06
     commun
    -0.06
    Compression
    -0.06
    middlewares
    -0.06
     ワ
    -0.06
     dough
    -0.06
     khiến
    -0.06
     CALLBACK
    -0.06
     cand
    -0.06
    POSITIVE LOGITS
    portlet
    0.06
    (axis
    0.06
    Cols
    0.06
     auditory
    0.06
    jší
    0.06
     nacional
    0.06
    심
    0.06
     diye
    0.06
    TypeID
    0.06
    ::::::::::::::::::::::::::::::::
    0.06
    Act Density 0.023%

    No Known Activations