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

    Neuronpedia

    INDEX
    Explanations

    arg

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ге
    -0.06
     instructional
    -0.06
     sf
    -0.06
    очные
    -0.06
    ’re
    -0.06
    .review
    -0.06
    менш
    -0.06
     architect
    -0.06
     adapter
    -0.06
    cdr
    -0.06
    POSITIVE LOGITS
     unconstitutional
    0.07
    (Key
    0.07
    );"
    0.06
    _article
    0.06
     bulunduğu
    0.06
    стров
    0.06
    /examples
    0.06
    TIMER
    0.06
    arsimp
    0.06
    dsl
    0.06
    Act Density 0.007%

    No Known Activations