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

    Neuronpedia

    INDEX
    Explanations

    your name or signature

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     mins
    0.62
    ometer
    0.61
    حص
    0.61
    嗔
    0.58
    CategoryID
    0.57
     kingdom
    0.56
    скоп
    0.55
    近い
    0.55
    描述
    0.54
     Indus
    0.53
    POSITIVE LOGITS
    firstname
    0.98
    FirstName
    0.97
     Last
    0.94
     firstname
    0.91
    Surname
    0.91
    lastname
    0.91
    fname
    0.90
    Last
    0.88
    surname
    0.88
     lastname
    0.88
    Act Density 0.236%

    No Known Activations