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

    Neuronpedia

    INDEX
    Explanations

    Python class __init__ methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    이는
    0.82
    ron
    0.75
    sman
    0.75
    ,
    0.75
    aians
    0.74
    yta
    0.74
    horas
    0.73
    omme
    0.73
    스는
    0.72
    ai
    0.72
    POSITIVE LOGITS
    น
    1.12
    in
    1.08
    н
    1.02
    न
    1.02
    ン
    0.99
    n
    0.97
    은
    0.95
    ın
    0.92
    ه
    0.91
    は
    0.91
    Act Density 0.032%

    No Known Activations