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

    Neuronpedia

    INDEX
    Explanations

    describing a manner or method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     प्रतिदिन
    0.71
    irling
    0.70
    imately
    0.68
    ari
    0.67
    aya
    0.67
     буду
    0.67
    ara
    0.66
    agan
    0.66
    ata
    0.65
     тексту
    0.65
    POSITIVE LOGITS
    t
    0.86
    1
    0.77
    D
    0.74
    י
    0.73
    就
    0.73
    Do
    0.72
    ский
    0.72
    OK
    0.70
    ž
    0.70
    DataAccess
    0.69
    Act Density 0.005%

    No Known Activations