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

    Neuronpedia

    INDEX
    Explanations

    engine

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    udge
    -0.08
    atial
    -0.07
     beams
    -0.07
     rainfall
    -0.07
     anlaşma
    -0.07
     drained
    -0.07
    켈
    -0.06
    Plug
    -0.06
    posing
    -0.06
    メニュー
    -0.06
    POSITIVE LOGITS
     生
    0.08
    ⻁
    0.07
    $smarty
    0.07
     Jian
    0.07
    .characters
    0.07
    (co
    0.07
    .shopping
    0.07
    噬
    0.07
     @
    0.07
    찮
    0.07
    Act Density 0.001%

    No Known Activations