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

    Neuronpedia

    INDEX
    Explanations

    function

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .onPause
    -0.07
    _REGION
    -0.07
    להלן
    -0.07
    .Println
    -0.07
     qDebug
    -0.07
     gastrointestinal
    -0.06
     tras
    -0.06
    “Yes
    -0.06
    京剧
    -0.06
     daher
    -0.06
    POSITIVE LOGITS
     reflected
    0.07
     tokenizer
    0.07
    onus
    0.07
    -binding
    0.07
     padding
    0.07
    vais
    0.07
     prison
    0.07
     matched
    0.07
    anners
    0.07
     ℝ
    0.07
    Act Density 0.004%

    No Known Activations