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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "make."

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

    Code snippets or foreign languages

    np_acts-logits-general · gemini-2.0-flash

    specific semantic categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    StandardCharsets
    -0.71
    Gön
    -0.50
     مشين
    -0.48
    ADVERTISEMENT
    -0.46
    BeginInit
    -0.46
    élo
    -0.46
     seat
    -0.46
    bodyParser
    -0.45
    ulman
    -0.45
    -0.45
    POSITIVE LOGITS
    الإنجليزية
    0.65
    ⓘ
    0.58
    KURZBESCHREIBUNG
    0.57
     mixture
    0.55
    //}
    0.54
    kloped
    0.54
    újo
    0.53
    Vidite
    0.52
     Mixture
    0.52
     mixtures
    0.52
    Act Density 0.077%

    No Known Activations