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

    Neuronpedia

    INDEX
    Explanations

    Bach

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hazard
    -1.34
    Hazard
    -1.23
     hazard
    -1.19
    hazard
    -1.18
    buck
    -1.08
     HAZARD
    -1.04
     buck
    -0.90
    HAZ
    -0.87
     hazards
    -0.84
     Hazards
    -0.81
    POSITIVE LOGITS
    TypedDataSet
    0.57
    s
    0.50
    ary
    0.47
    soft
    0.47
    le
    0.46
    o
    0.46
    sl
    0.45
    spy
    0.45
     gepubliceerd
    0.45
    let
    0.45
    Act Density 0.014%

    No Known Activations