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

    Neuronpedia

    INDEX
    Explanations

    closing brackets and descriptions in code

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

    Objective-C initializer keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apiece
    -0.33
    Same
    -0.32
     convierten
    -0.32
     preocup
    -0.30
     pregunto
    -0.28
     convierte
    -0.28
    Con
    -0.28
     comesti
    -0.28
    attendre
    -0.27
    Ready
    -0.27
    POSITIVE LOGITS
    0.88
     kasarigan
    0.79
     للمعارف
    0.77
    bkz
    0.75
    IntoConstraints
    0.75
    ValueStyle
    0.74
    nonatomic
    0.73
    OGND
    0.71
     otomatig
    0.71
    devamını
    0.70
    Act Density 0.007%

    No Known Activations