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

    Neuronpedia

    INDEX
    Explanations

    morpheme

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ateral
    0.80
     nove
    0.77
    enschaft
    0.77
     Hospitality
    0.76
     Laboratory
    0.74
     spraw
    0.74
     dismal
    0.74
     distant
    0.73
     یورپی
    0.73
     twee
    0.71
    POSITIVE LOGITS
    ORA
    0.86
    CHO
    0.84
    POINT
    0.82
    iendo
    0.81
    POE
    0.78
     estatura
    0.77
    ی
    0.77
    STATS
    0.77
    OCCO
    0.77
    絴
    0.75
    Act Density 0.002%

    No Known Activations