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

    Neuronpedia

    INDEX
    Explanations

    intellectual property and developers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Vend
    0.45
     tongue
    0.43
    હાર
    0.43
    tong
    0.42
     cim
    0.39
    datad
    0.39
     io
    0.39
     സന്ത
    0.39
     tongues
    0.38
    isVideoRecording
    0.38
    POSITIVE LOGITS
     READING
    0.42
     squeezing
    0.39
     displaying
    0.38
     squeeze
    0.38
     billions
    0.37
    堵
    0.37
    Reading
    0.36
    SHUNT
    0.36
     зміни
    0.36
     variations
    0.36
    Act Density 0.038%

    No Known Activations