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

    Neuronpedia

    INDEX
    Explanations

    http

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     формы
    -0.07
    ıldığı
    -0.06
    스는
    -0.06
    .frequency
    -0.06
    _active
    -0.06
     shareholder
    -0.06
    peri
    -0.06
     mnoho
    -0.06
    .Writer
    -0.06
    �
    -0.06
    POSITIVE LOGITS
     Pulitzer
    0.07
    mux
    0.06
     ніч
    0.06
     {{↵
    0.06
    SingleNode
    0.06
    _war
    0.06
     ними
    0.06
     zarar
    0.06
    _Category
    0.06
     Om
    0.06
    Act Density 0.002%

    No Known Activations