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

    Neuronpedia

    INDEX
    Explanations

    passages that discuss governmental or institutional financial support and policy changes

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

    Preceding punctuation or math symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Center
    -0.67
     CENTER
    -0.66
    CENTER
    -0.66
    Diweddarwch
    -0.64
    Center
    -0.63
     poveznice
    -0.63
    center
    -0.63
     dépla
    -0.58
     center
    -0.57
     Offense
    -0.57
    POSITIVE LOGITS
     Messrs
    0.66
     wireType
    0.60
    ümüz
    0.58
     ProtoMessage
    0.54
    водится
    0.52
    Injectable
    0.50
     rapat
    0.48
    saya
    0.47
     angegeben
    0.47
     malos
    0.47
    Act Density 0.200%

    No Known Activations