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

    Neuronpedia

    INDEX
    Explanations

    .com

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    constexpr
    -0.07
    送料
    -0.07
    ustralia
    -0.06
     Kelley
    -0.06
    eventType
    -0.06
     [@
    -0.06
     palette
    -0.06
     runway
    -0.06
    $time
    -0.06
    uplic
    -0.06
    POSITIVE LOGITS
    -col
    0.07
    (train
    0.07
     extra
    0.07
     guts
    0.07
    唱
    0.07
     tops
    0.06
     支
    0.06
    (cond
    0.06
     drying
    0.06
    urb
    0.06
    Act Density 0.003%

    No Known Activations