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

    Neuronpedia

    INDEX
    Explanations

    digitized books

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     qualification
    0.89
     combination
    0.84
     relegated
    0.81
     A
    0.80
     lineup
    0.80
    atility
    0.79
     confines
    0.78
     qualifications
    0.77
     typesetting
    0.76
    de
    0.75
    POSITIVE LOGITS
     río
    0.94
     erne
    0.88
     bitOp
    0.86
     puiss
    0.80
     espagn
    0.80
     Бер
    0.80
     licht
    0.79
    ረስ
    0.79
    حيان
    0.79
     Rever
    0.78
    Act Density 0.002%

    No Known Activations