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

    Neuronpedia

    INDEX
    Explanations

    defining terms

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (hex
    -0.07
    However
    -0.07
    ساب
    -0.07
    赏
    -0.06
     ":
    -0.06
    annotate
    -0.06
     ceil
    -0.06
     hız
    -0.06
     conocer
    -0.06
    じ
    -0.06
    POSITIVE LOGITS
     East
    0.07
     intermittent
    0.07
    .sys
    0.07
    _Create
    0.07
    -fetch
    0.06
    演员
    0.06
     Invisible
    0.06
     pracę
    0.06
    téri
    0.06
    类产品
    0.06
    Act Density 0.008%

    No Known Activations