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

    Neuronpedia

    INDEX
    Explanations

    the beginning of a document or section, indicated by a specific marker

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

    preceding quotation marks

    np_acts-logits-general · gemini-2.0-flash

    start of sentence after punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    featureID
    -0.78
    Personendaten
    -0.74
    sidemargin
    -0.73
    OGND
    -0.69
    InitVars
    -0.68
    webElementXpaths
    -0.65
    kloped
    -0.60
     دیکھیے
    -0.58
    Попис
    -0.57
    XmlAccessorType
    -0.56
    POSITIVE LOGITS
     BoxDecoration
    0.79
     berupa
    0.67
     تضيفلها
    0.63
    mitives
    0.56
    ubin
    0.55
     الحره
    0.54
    ärzt
    0.53
     مرئيه
    0.52
     msglen
    0.52
    heritance
    0.52
    Act Density 0.015%

    No Known Activations