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

    Neuronpedia

    INDEX
    Explanations

    water and contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ો
    0.79
    annter
    0.78
    ्ज
    0.73
    بيت
    0.72
    ්
    0.72
    tes
    0.70
    ted
    0.70
    athar
    0.69
    więks
    0.68
    zw
    0.68
    POSITIVE LOGITS
    logged
    1.98
    melon
    1.43
    logging
    1.38
     vapour
    1.35
    colours
    1.29
     vapor
    1.28
     polo
    1.25
    courses
    1.23
    fowl
    1.22
     soluble
    1.21
    Act Density 0.060%

    No Known Activations