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

    Neuronpedia

    INDEX
    Explanations

    code statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ()]
    0.70
    ())),
    0.69
    ()),
    0.66
    (),
    0.65
    ()));
    0.64
    ']));
    0.62
    ಿಸಿದ್ದಾರೆ
    0.62
    ()],
    0.62
     anion
    0.61
     ऋषि
    0.61
    POSITIVE LOGITS
    クマ
    0.71
    kul
    0.69
     moo
    0.64
    l
    0.62
     நாட்க
    0.61
     зло
    0.60
    ড়ার
    0.60
     lahan
    0.60
    Final
    0.60
     tum
    0.59
    Act Density 0.139%

    No Known Activations