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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ZONE
    -0.07
     compact
    -0.06
     έκ
    -0.06
    masters
    -0.06
    .handler
    -0.06
     próp
    -0.06
     Eigen
    -0.06
     dbl
    -0.06
     IDX
    -0.06
    直
    -0.06
    POSITIVE LOGITS
     Jud
    0.06
     Goldman
    0.06
     Cann
    0.06
    _ROUT
    0.06
    -det
    0.06
    [maxn
    0.06
     nude
    0.06
     Cardio
    0.05
    -fill
    0.05
    \:
    0.05
    Act Density 0.018%

    No Known Activations