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

    Neuronpedia

    INDEX
    Explanations

    HTML class attributes in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    element class names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Билгалдахарш
    -0.60
    IBOutlet
    -0.60
    /**
    -0.60
    تفصیلات
    -0.59
     noDo
    -0.59
     protoimpl
    -0.58
    erover
    -0.57
    <bos>
    -0.57
     pops
    -0.56
     Bolts
    -0.56
    POSITIVE LOGITS
    className
    1.27
     className
    1.13
    ClassName
    0.98
    getClassName
    0.85
    classnames
    0.64
    classname
    0.57
     classNames
    0.52
    ActionMode
    0.50
    Name
    0.48
    appName
    0.44
    Act Density 0.001%

    No Known Activations