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

    Neuronpedia

    INDEX
    Explanations

    reserve requirements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ेंद
    0.46
    ара
    0.42
    ্বরূপ
    0.41
    razol
    0.40
    鉗
    0.38
     onlyOwner
    0.38
    ட்டான
    0.37
    ^*(\
    0.37
     cytometry
    0.37
    ˧
    0.37
    POSITIVE LOGITS
    unin
    0.41
     converted
    0.39
    Converted
    0.38
    ffine
    0.38
     georg
    0.37
    Perhaps
    0.37
    FullName
    0.36
    გუფი
    0.36
     Georg
    0.35
    เขต
    0.35
    Act Density 0.001%

    No Known Activations