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

    Neuronpedia

    INDEX
    Explanations

    ranges with numbers and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     However
    -1.77
     from
    -1.71
     '
    -1.71
     Also
    -1.63
     In
    -1.56
     will
    -1.54
     because
    -1.50
    "--
    -1.45
     Because
    -1.45
     which
    -1.41
    POSITIVE LOGITS
    鶿
    1.93
    谖
    1.61
    擼
    1.61
    慙
    1.61
    좆
    1.59
    鶘
    1.57
    ჻
    1.57
     visse
    1.55
    摃
    1.52
    焢
    1.51
    Act Density 0.076%

    No Known Activations