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

    Neuronpedia

    INDEX
    Explanations

    Dialog

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    十七条
    -0.07
    _FILENAME
    -0.07
    gráfica
    -0.07
    teen
    -0.06
     fig
    -0.06
    畸形
    -0.06
    _classifier
    -0.06
    summary
    -0.06
    ⺟
    -0.06
     sözleşme
    -0.06
    POSITIVE LOGITS
    _ACTIVITY
    0.08
    �
    0.08
     شي
    0.07
    (Configuration
    0.07
    (dl
    0.07
    自
    0.07
    던
    0.07
    毽
    0.07
    ,↵
    0.07
    Solo
    0.07
    Act Density 0.971%

    No Known Activations