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

    Neuronpedia

    INDEX
    Explanations

    references to various forms of goodness and value in multiple contexts

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

    specific nouns and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     يتيمه
    -0.75
    GEBURTSDATUM
    -0.68
    ConstraintMaker
    -0.67
     المعيارى
    -0.66
     الحره
    -0.65
    MLLoader
    -0.63
    AddHtmlAttribute
    -0.62
     Normdatei
    -0.62
    Vidite
    -0.62
    IntoConstraints
    -0.59
    POSITIVE LOGITS
     giants
    0.31
    фро
    0.29
    bkz
    0.28
     gigantes
    0.27
     号
    0.27
     basta
    0.26
    сур
    0.25
     devices
    0.25
     ador
    0.25
     gadgets
    0.25
    Act Density 0.088%

    No Known Activations