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

    Neuronpedia

    INDEX
    Explanations

    comma

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Monitoring
    -0.07
     counselling
    -0.07
    ----------------
    -0.06
     monitoring
    -0.06
    Thu
    -0.06
    ‌کن
    -0.06
     موتور
    -0.06
     Vinci
    -0.06
     disasters
    -0.06
    .MON
    -0.06
    POSITIVE LOGITS
     этом
    0.07
     ense
    0.07
    _sample
    0.06
     हम
    0.06
     hogy
    0.06
     참
    0.06
     invokingState
    0.06
    inizi
    0.06
     hủy
    0.06
     разм
    0.06
    Act Density 0.004%

    No Known Activations