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

    Neuronpedia

    INDEX
    Explanations

    utility rates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    cursor
    -0.07
     shaded
    -0.07
     ']
    -0.06
    码
    -0.06
    _,↵
    -0.06
    great
    -0.06
    ]↵↵
    -0.06
    碼
    -0.06
    eczy
    -0.06
    」
    -0.06
    POSITIVE LOGITS
    _holder
    0.07
     Trend
    0.06
    риф
    0.06
     preserves
    0.06
     البل
    0.06
     《
    0.06
    .child
    0.06
    opyright
    0.06
     استخدام
    0.06
     الوط
    0.06
    Act Density 0.042%

    No Known Activations