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

    Neuronpedia

    INDEX
    Explanations

    the use of the variable 'i' in code loops

    oai_token-act-pair · gemini-2.0-flash

    i

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    addCriterion
    -0.73
     مشين
    -0.72
    DrawerToggle
    -0.64
    WebServlet
    -0.61
     autorytatywna
    -0.60
     transfieras
    -0.60
    CloseOperation
    -0.59
    Personendaten
    -0.59
    Autoritní
    -0.59
    -0.59
    POSITIVE LOGITS
     am
    0.57
     když
    0.47
     degré
    0.42
    itial
    0.41
    cicle
    0.40
     boty
    0.40
    мить
    0.38
     suppose
    0.38
    rs
    0.38
    boys
    0.37
    Act Density 1.525%

    No Known Activations