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

    Neuronpedia

    INDEX
    Explanations

    relatively friendly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    g
    0.65
    p
    0.60
    r
    0.58
    y
    0.56
    k
    0.56
    h
    0.54
    e
    0.52
    m
    0.52
    l
    0.50
    u
    0.48
    POSITIVE LOGITS
     સમય
    0.62
     vegetarian
    0.55
    皤
    0.52
     `<=`
    0.52
     stabilize
    0.50
     Vegetarian
    0.50
    曉
    0.49
     menghadapi
    0.49
     Miao
    0.49
     લગભગ
    0.49
    Act Density 0.000%

    No Known Activations