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

    Neuronpedia

    INDEX
    Explanations

    expressions of disbelief or negation

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

    it's followed by adjective or past participle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    InjectAttribute
    -0.50
    limsy
    -0.48
    rungsseite
    -0.46
     itſelf
    -0.46
    __(/*!
    -0.43
     Shallow
    -0.40
     themſelves
    -0.40
    XmlAccessType
    -0.39
     contextLoads
    -0.39
    뉜
    -0.39
    POSITIVE LOGITS
    webElementXpaths
    0.61
    ✷
    0.40
     locus
    0.40
     TextAppearance
    0.40
     nawr
    0.39
     EClass
    0.39
    endpush
    0.38
    évaluateur
    0.38
    Jegyzetek
    0.37
    ündigung
    0.37
    Act Density 0.016%

    No Known Activations