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

    Neuronpedia

    INDEX
    Explanations

    background = "lightgreen"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ț
    0.92
     luận
    0.86
    ଝ
    0.85
    ṱ
    0.83
     élevée
    0.83
    țit
    0.83
     olhar
    0.82
    畯
    0.82
    대의
    0.82
     yapılan
    0.82
    POSITIVE LOGITS
    iu
    0.89
     काम
    0.84
     plasmids
    0.82
     governors
    0.78
     mam
    0.76
     probative
    0.76
     parades
    0.75
    رام
    0.73
     nurseries
    0.73
    ipp
    0.73
    Act Density 0.000%

    No Known Activations