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

    Neuronpedia

    INDEX
    Explanations

    punctuation/conjunctions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EDGE
    -0.07
     blacks
    -0.07
     resin
    -0.07
    ilies
    -0.06
     wings
    -0.06
    (Card
    -0.06
    우
    -0.06
    _tree
    -0.06
    /send
    -0.06
     Benz
    -0.06
    POSITIVE LOGITS
    ोख
    0.07
     требования
    0.06
     arrog
    0.06
    ’un
    0.06
    inery
    0.06
     barcelona
    0.06
    рина
    0.06
    eko
    0.06
    .getWorld
    0.06
     proport
    0.06
    Act Density 0.043%

    No Known Activations