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

    Neuronpedia

    INDEX
    Explanations

    movie titles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     whip
    -0.07
     rud
    -0.07
    Art
    -0.07
     extracts
    -0.07
     Lee
    -0.07
     松
    -0.07
    sv
    -0.07
    capt
    -0.06
     panorama
    -0.06
    Lee
    -0.06
    POSITIVE LOGITS
    pecial
    0.07
    函
    0.06
    .Extensions
    0.06
    則
    0.06
    PECT
    0.06
    нг
    0.06
    كز
    0.06
    ительность
    0.06
    agnostic
    0.06
     Restricted
    0.06
    Act Density 0.038%

    No Known Activations