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

    Neuronpedia

    INDEX
    Explanations

    word boundary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    و
    1.20
     &
    0.95
    able
    0.93
     Stones
    0.92
    ため
    0.91
     pedag
    0.91
     колле
    0.91
     Tamp
    0.89
     nhiệm
    0.89
     educativo
    0.88
    POSITIVE LOGITS
    roa
    0.98
    醀
    0.94
    BibitemOpen
    0.93
    ب
    0.93
    ки
    0.91
    слав
    0.89
    د
    0.89
    nnet
    0.88
    ಾನೂ
    0.88
     defunct
    0.86
    Act Density 0.002%

    No Known Activations