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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     يع
    -0.07
    OOM
    -0.07
    :])
    -0.06
    เรา
    -0.06
    _ST
    -0.06
     vět
    -0.06
     judged
    -0.06
     ощ
    -0.06
     зрозум
    -0.06
    
    -0.06
    POSITIVE LOGITS
    ulp
    0.07
    -error
    0.07
    代
    0.07
    (error
    0.07
     leased
    0.06
    celand
    0.06
     anterior
    0.06
    ogui
    0.06
     поперед
    0.06
    Warning
    0.06
    Act Density 0.000%

    No Known Activations