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

    Neuronpedia

    INDEX
    Explanations

    words related to physical conditions or actions involving health

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

    followed by unusual punctuation

    np_acts-logits-general · gemini-2.0-flash

    words related to beginnings or endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.65
    MLLoader
    -0.58
    IntoConstraints
    -0.57
     InputDecoration
    -0.52
    VYMaps
    -0.49
     ویکی‌پدی
    -0.46
    ंदीखरीदारी
    -0.45
    AccessorTable
    -0.45
    piram
    -0.44
     Administrativna
    -0.42
    POSITIVE LOGITS
     îna
    0.39
     rhestr
    0.36
    iferous
    0.35
     تانيه
    0.35
    penn
    0.35
    PREFIX
    0.35
    mitglied
    0.35
     jagung
    0.35
     certo
    0.34
    delimiter
    0.34
    Act Density 0.197%

    No Known Activations