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

    Neuronpedia

    INDEX
    Explanations

    punctuation and sentence structure elements

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

    Followed by capitalized words

    np_acts-logits-general · gemini-2.0-flash

    numbers and punctuation endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ogóle
    -0.44
    Nay
    -0.36
     katanya
    -0.35
     veille
    -0.35
    万一
    -0.35
    actually
    -0.35
     rou
    -0.35
    Canto
    -0.34
    tinta
    -0.34
     veta
    -0.33
    POSITIVE LOGITS
     estekak
    0.59
    Хьажоргаш
    0.58
    setVerticalGroup
    0.58
     informée
    0.53
     HasFactory
    0.53
     تضيفلها
    0.51
     tartalomajánló
    0.51
    OCCURRED
    0.49
    __(/*!
    0.49
    Tembelea
    0.48
    Act Density 0.207%

    No Known Activations