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

    Neuronpedia

    INDEX
    Explanations

    how competitive or easy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     کمپیوٹر
    0.55
     পেয়েছেন
    0.52
    графі
    0.52
     plă
    0.50
    ﾙ
    0.49
     ڈاکٹر
    0.49
    يكون
    0.49
     aște
    0.48
     애니
    0.48
    轵
    0.48
    POSITIVE LOGITS
    in
    0.77
    t
    0.75
    p
    0.65
    www
    0.63
    n
    0.63
    v
    0.59
    c
    0.59
    inv
    0.58
    ch
    0.57
    al
    0.57
    Act Density 0.001%

    No Known Activations