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

    Neuronpedia

    INDEX
    Explanations

    colons and the structure of lists or enumerations

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

    book, movie, or exhibition titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     légitime
    -0.42
     flesta
    -0.40
     Könige
    -0.36
     fleste
    -0.35
     inférieure
    -0.35
     Negra
    -0.35
     vuestros
    -0.35
    GOTREF
    -0.34
     Sociales
    -0.34
     normalidad
    -0.34
    POSITIVE LOGITS
    Tembelea
    0.81
     nakalista
    0.69
     تضيفلها
    0.69
    Ӕ
    0.63
    ⓧ
    0.60
    شهاد
    0.58
     itſelf
    0.58
     NAC
    0.58
    abestanden
    0.57
    WireFormatLite
    0.57
    Act Density 0.025%

    No Known Activations