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

    Neuronpedia

    INDEX
    Explanations

    hua University

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    INSTDIR
    0.55
    InstrumentedTest
    0.52
     الدم
    0.52
    HNO
    0.52
    راجعه
    0.52
    的研究
    0.51
    功
    0.49
    ካከል
    0.49
    POV
    0.48
     മാത്രമേ
    0.48
    POSITIVE LOGITS
    in
    0.83
    an
    0.83
    is
    0.72
    es
    0.70
    il
    0.70
    it
    0.68
    et
    0.63
    im
    0.63
    rows
    0.63
    ur
    0.60
    Act Density 0.000%

    No Known Activations