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

    Neuronpedia

    INDEX
    Explanations

    automated content and deployment

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     EVs
    0.50
    YNAMIC
    0.48
     RMSE
    0.47
    を用いる
    0.47
     SSP
    0.47
     використову
    0.46
     ETFs
    0.46
     STATIC
    0.44
     ………………………………..
    0.43
    ಿಕೆಯ
    0.43
    POSITIVE LOGITS
    to
    0.66
    i
    0.59
    from
    0.54
    at
    0.53
    so
    0.46
    height
    0.46
    right
    0.46
    lt
    0.46
    down
    0.46
    label
    0.45
    Act Density 0.001%

    No Known Activations