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

    Neuronpedia

    INDEX
    Explanations

    technical terminology related to coding and programming errors

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

    Followed by an attempt, try, or is

    np_acts-logits-general · gemini-2.0-flash

    trying to complete an action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     '\\;'
    -0.73
     ſte
    -0.71
    Aholisi
    -0.69
     Houſe
    -0.69
     houſe
    -0.69
     ſch
    -0.69
     pleaſure
    -0.68
    parsedMessage
    -0.66
     queſta
    -0.66
     Reſ
    -0.66
    POSITIVE LOGITS
     cả
    0.35
    金
    0.34
     맞
    0.33
     rightfully
    0.31
    used
    0.30
     ļ
    0.29
    力
    0.29
    long
    0.29
    bind
    0.29
     i
    0.29
    Act Density 1.197%

    No Known Activations