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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     clauses
    -0.07
     nj
    -0.06
     kullanılır
    -0.06
    Ser
    -0.06
     volcanic
    -0.06
     sensit
    -0.06
    이션
    -0.06
    _delete
    -0.06
     landscape
    -0.06
     sugars
    -0.06
    POSITIVE LOGITS
    撃
    0.06
    _secs
    0.06
    حدة
    0.06
    _RDWR
    0.06
    (Tile
    0.06
    AFF
    0.06
     отвер
    0.06
    午
    0.06
    _QUESTION
    0.06
    如下
    0.06
    Act Density 0.004%

    No Known Activations