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

    Neuronpedia

    INDEX
    Explanations

    "like" or "as" in many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    1.27
    س
    1.15
    p
    1.13
    y
    1.10
    g
    1.07
    m
    1.01
    d
    0.96
    to
    0.94
    น
    0.89
     of
    0.87
    POSITIVE LOGITS
     precluded
    0.78
     하지만
    0.75
     أم
    0.74
     ו
    0.72
     ಲಾ
    0.71
    జేపీ
    0.71
    albeit
    0.71
    ань
    0.70
     بر
    0.70
    ות
    0.68
    Act Density 0.001%

    No Known Activations