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

    Neuronpedia

    INDEX
    Explanations

    acknowledges potential

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bodyParser
    0.46
    니다
    0.45
    PlistBuddy
    0.44
    ו
    0.44
     twenties
    0.44
     construye
    0.44
    的事情
    0.44
    よりも
    0.44
     griega
    0.44
     গান
    0.43
    POSITIVE LOGITS
     initiating
    0.49
    for
    0.49
     initiated
    0.47
     initiates
    0.46
     flagged
    0.45
    ou
    0.45
    elle
    0.44
    abang
    0.44
    etem
    0.44
     Highland
    0.43
    Act Density 0.000%

    No Known Activations