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

    Neuronpedia

    INDEX
    Explanations

    names and initials like ROY G. BIV

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    5
    0.93
    :
    0.79
    8
    0.79
     cataly
    0.73
     displeasure
    0.71
    4
    0.70
    Ⲱ
    0.69
     whiteboard
    0.68
     revital
    0.68
    (
    0.68
    POSITIVE LOGITS
    d
    1.19
    the
    1.14
    t
    1.13
    v
    1.04
    f
    0.96
    ال
    0.95
    an
    0.94
     the
    0.82
    ↵↵
    0.78
    g
    0.78
    Act Density 0.048%

    No Known Activations