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

    Neuronpedia

    INDEX
    Explanations

    quotation marks/brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     blk
    -0.07
    ython
    -0.06
     Picks
    -0.06
    cover
    -0.06
    <Post
    -0.06
     Bio
    -0.06
     Gow
    -0.06
    _Init
    -0.06
    defines
    -0.06
     Fiber
    -0.06
    POSITIVE LOGITS
    ي
    0.07
    .ab
    0.07
     욕
    0.07
    rání
    0.07
    ologists
    0.06
    .actual
    0.06
    vide
    0.06
    rails
    0.06
    staticmethod
    0.06
     exped
    0.06
    Act Density 0.103%

    No Known Activations