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

    Neuronpedia

    INDEX
    Explanations

    News and technical content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eview
    -0.07
    compose
    -0.07
    .close
    -0.06
    process
    -0.06
     Color
    -0.06
    Returns
    -0.06
     tur
    -0.06
    PropertyValue
    -0.06
     xảy
    -0.06
     플
    -0.06
    POSITIVE LOGITS
     SVM
    0.07
     被
    0.07
    _way
    0.07
     Zend
    0.06
    _modify
    0.06
     레이
    0.06
    initialized
    0.06
    OOM
    0.06
     جوان
    0.06
     Documentation
    0.06
    Act Density 0.044%

    No Known Activations