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

    Neuronpedia

    INDEX
    Explanations

    watermark and copyright

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    viaf
    -0.81
     TextInputType
    -0.75
     contradiction
    -0.73
    responseType
    -0.71
     borrow
    -0.71
    шений
    -0.70
     MSN
    -0.69
     contradictions
    -0.69
    ويات
    -0.68
     governing
    -0.67
    POSITIVE LOGITS
     watermark
    3.53
     water
    3.45
    water
    2.84
     Water
    2.83
    watermark
    2.67
    Water
    2.64
    Watermark
    2.58
    WATER
    2.50
     WATER
    2.45
    水
    2.42
    Act Density 0.031%

    No Known Activations