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

    Neuronpedia

    INDEX
    Explanations

    Serif, MSVC

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Zumba
    0.62
     женщина
    0.61
     biomedical
    0.59
     astronomer
    0.59
     sentença
    0.59
     약
    0.57
    n
    0.57
     hamster
    0.57
     воен
    0.56
     biomed
    0.56
    POSITIVE LOGITS
    E
    1.02
    و
    1.01
    ہ
    0.91
    V
    0.88
     on
    0.85
    گ
    0.82
    ق
    0.82
    Y
    0.80
    I
    0.78
    of
    0.76
    Act Density 0.000%

    No Known Activations