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

    Neuronpedia

    INDEX
    Explanations

    Code/data formats

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    parallel
    -0.07
    ContentLoaded
    -0.06
    Nh
    -0.06
    :focus
    -0.06
     củ
    -0.06
    pix
    -0.06
    dw
    -0.06
    _snd
    -0.06
    prevState
    -0.06
    Inlining
    -0.06
    POSITIVE LOGITS
     fallout
    0.08
     enam
    0.07
     benefit
    0.07
     dub
    0.07
     suburbs
    0.06
    陽
    0.06
     Routine
    0.06
    abet
    0.06
    defense
    0.06
     kon
    0.06
    Act Density 0.006%

    No Known Activations