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

    Neuronpedia

    INDEX
    Explanations

    URL path segments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    с
    1.11
    س
    1.05
    L
    0.96
    ’
    0.95
    C
    0.84
    ก
    0.75
    اخ
    0.73
    S
    0.71
    Data
    0.70
    נ
    0.70
    POSITIVE LOGITS
     to
    0.96
     by
    0.85
    лло
    0.82
    ۹
    0.81
    ="/
    0.79
     AppBsky
    0.79
    inę
    0.75
    inį
    0.74
    ༦
    0.74
     antigens
    0.73
    Act Density 0.002%

    No Known Activations