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

    Neuronpedia

    INDEX
    Explanations

    improvements and

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ampang
    0.31
    ベルト
    0.31
     نیند
    0.31
     keyDown
    0.30
     tricky
    0.29
    NOMBRE
    0.29
     invers
    0.29
     Ambedkar
    0.29
    uthers
    0.29
    azim
    0.29
    POSITIVE LOGITS
     थी
    0.29
    “
    0.29
    ///
    0.28
    smtp
    0.28
    nik
    0.28
    ://
    0.27
    över
    0.27
     yì
    0.27
    ִי
    0.27
    ially
    0.26
    Act Density 0.003%

    No Known Activations