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

    Neuronpedia

    INDEX
    Explanations

    "output:" label and results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1.24
    ۲
    1.13
    える
    1.03
    스
    1.02
    с
    0.98
    ेंगू
    0.95
    ९
    0.94
     altri
    0.93
     mendapat
    0.93
    ない
    0.92
    POSITIVE LOGITS
    the
    1.50
    an
    1.43
    u
    1.41
    a
    1.38
    1
    1.34
    it
    1.30
    at
    1.27
    ten
    1.21
     Output
    1.16
    ere
    1.16
    Act Density 0.095%

    No Known Activations