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

    Neuronpedia

    INDEX
    Explanations

    terms related to programming language features and comparisons

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

    no difference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :✨
    -0.46
     @"/
    -0.46
     prohibido
    -0.46
    VYMaps
    -0.45
    eseorang
    -0.45
    Aholisi
    -0.44
     CanadaChoose
    -0.43
    aarrggbb
    -0.43
     potentiel
    -0.42
     volcán
    -0.42
    POSITIVE LOGITS
    styleType
    0.40
     merken
    0.40
    UseVisualStyle
    0.39
    zessin
    0.38
    ніципалі
    0.38
     AttributeSet
    0.38
     invokingState
    0.37
    дна
    0.37
    indra
    0.36
     any
    0.36
    Act Density 0.178%

    No Known Activations