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

    Neuronpedia

    INDEX
    Explanations

    I

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    skému
    -0.08
    _views
    -0.07
     Cinema
    -0.07
     explor
    -0.07
    _vars
    -0.06
    uron
    -0.06
     hardly
    -0.06
     tended
    -0.06
    ункт
    -0.06
    movie
    -0.06
    POSITIVE LOGITS
    pile
    0.06
     zaz
    0.06
    zek
    0.06
     土
    0.06
     art
    0.06
    :id
    0.06
    OTT
    0.05
     Surre
    0.05
     гри
    0.05
     Chest
    0.05
    Act Density 0.037%

    No Known Activations