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

    Neuronpedia

    INDEX
    Explanations

    numbers and ratings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     epilept
    0.24
     substring
    0.23
     groupBox
    0.23
     obfusc
    0.22
     attribut
    0.22
     appBar
    0.21
     subjekt
    0.21
     barbit
    0.21
     raster
    0.21
     elucidation
    0.21
    POSITIVE LOGITS
    0
    0.34
    of
    0.28
    а
    0.27
    4
    0.27
    3
    0.26
    0.26
    5
    0.26
    č
    0.26
    three
    0.24
    or
    0.24
    Act Density 0.319%

    No Known Activations