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

    Neuronpedia

    INDEX
    Explanations

    company or product names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    פ
    1.77
    го
    1.72
    про
    1.69
    ান
    1.60
    ों
    1.48
     chlorides
    1.48
    त
    1.40
    מ
    1.40
     palpable
    1.38
    setTextColor
    1.38
    POSITIVE LOGITS
    ية
    2.05
    ast
    1.95
    fully
    1.84
     Pública
    1.80
    eee
    1.66
    ai
    1.63
    ist
    1.63
    ang
    1.63
    e
    1.60
    m
    1.59
    Act Density 0.137%

    No Known Activations