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

    Neuronpedia

    INDEX
    Explanations

    standardized way to interface

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Calculating
    0.43
     Obstetrics
    0.40
    riks
    0.40
     Total
    0.39
     Audi
    0.39
     Packaging
    0.39
     Expo
    0.39
     reds
    0.39
     Assessing
    0.38
     Automotive
    0.38
    POSITIVE LOGITS
     laquelle
    0.43
     remerc
    0.41
    δη
    0.39
    ยาย
    0.39
     affirmative
    0.38
    源
    0.38
    ቱም
    0.38
     dicho
    0.37
     preferentially
    0.37
    真正
    0.37
    Act Density 0.003%

    No Known Activations