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

    Neuronpedia

    INDEX
    Explanations

    patterns and structural elements in data representations or coding syntax

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

    simon Dilley

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     betweenstory
    -0.49
     intptr
    -0.48
    KURZBESCHREIBUNG
    -0.45
    complexType
    -0.44
    transQ
    -0.43
     kasarigan
    -0.43
    GEBURTSDATUM
    -0.43
    enderror
    -0.42
    tanleria
    -0.42
    Havolalar
    -0.37
    POSITIVE LOGITS
     مشين
    0.47
     autorytatywna
    0.45
    Personensuche
    0.40
     secondly
    0.40
    Secondly
    0.39
     Secondly
    0.38
    rophes
    0.36
     Schweden
    0.34
    Geografía
    0.34
    ospatial
    0.34
    Act Density 0.085%

    No Known Activations