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

    Neuronpedia

    INDEX
    Explanations

    languages, notes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ಇದ್ದ
    0.43
    رحمن
    0.41
    yfik
    0.38
     pacote
    0.38
    ೂರ್ಯ
    0.38
    醌
    0.37
     QnrB
    0.37
    其
    0.36
    燹
    0.36
     svm
    0.36
    POSITIVE LOGITS
     notes
    0.73
     note
    0.70
    notes
    0.66
    Note
    0.65
     Notes
    0.65
     Note
    0.62
    Notes
    0.62
    written
    0.61
    note
    0.60
     written
    0.59
    Act Density 0.002%

    No Known Activations