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

    Neuronpedia

    INDEX
    Explanations

    durable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Autoritní
    -0.70
     Wikimedijinoj
    -0.67
     Paglinawan
    -0.64
     الرياضيه
    -0.62
     noDo
    -0.59
    ganu
    -0.59
    OGND
    -0.57
     calldata
    -0.57
    Personensuche
    -0.56
    MessageInfo
    -0.55
    POSITIVE LOGITS
    ($__
    0.60
    CloseOperation
    0.59
    :✨
    0.50
     مرئيه
    0.45
    rieux
    0.44
     quoi
    0.44
     meant
    0.44
     schick
    0.43
     people
    0.43
    onPressed
    0.42
    Act Density 0.020%

    No Known Activations