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

    Neuronpedia

    INDEX
    Explanations

    queries and expressions relating to existential questions and identity struggles

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

    Preceding certain punctuation or HTML tags

    np_acts-logits-general · gemini-2.0-flash

    semicolon after certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Jó
    -0.51
     \"
    -0.47
     n
    -0.47
    navigationItem
    -0.46
    siez
    -0.45
    InputLabel
    -0.45
     semi
    -0.44
    (\"
    -0.44
    dieran
    -0.43
     Tu
    -0.42
    POSITIVE LOGITS
    +#+
    0.89
    +#+#
    0.80
    Hentet
    0.79
    }();
    0.77
     فريبيس
    0.73
    verwijspagina
    0.73
     EconPapers
    0.72
     ***!
    0.72
    UnknownFields
    0.71
     ddelweddau
    0.71
    Act Density 0.075%

    No Known Activations