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

    Neuronpedia

    INDEX
    Explanations

    instances and classes related to object-oriented programming concepts, particularly focusing on subtypes and their attributes

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

    isinstance or class/subclass relationships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     StringTokenizer
    -0.45
    parsedMessage
    -0.45
    exitRule
    -0.44
    ']>;
    -0.42
     Welle
    -0.41
    aimer
    -0.41
     ProtoMessage
    -0.40
    лтемелер
    -0.40
    getJSONArray
    -0.39
    SourceChecksum
    -0.38
    POSITIVE LOGITS
    rungsseite
    0.47
     scorso
    0.43
    paramref
    0.42
    aClass
    0.42
     autorytatywna
    0.41
     nakalista
    0.40
     instanceof
    0.39
     cref
    0.37
     fianco
    0.37
     Tory
    0.37
    Act Density 0.118%

    No Known Activations