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

    Neuronpedia

    INDEX
    Explanations

    references to organizational structures or classifications in documents

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

    before the suffix "s"

    np_acts-logits-general · gemini-2.0-flash

    plural endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    interopRequire
    -0.77
    сылкі
    -0.71
    ‌ی
    -0.68
    nolia
    -0.63
    \{\\
    -0.61
    ostante
    -0.58
    rainian
    -0.56
    stalline
    -0.55
    ISODE
    -0.54
    ReusableCell
    -0.54
    POSITIVE LOGITS
    s
    3.85
    ی
    1.63
    ы
    1.48
    ים
    1.40
    ся
    1.35
    ات
    1.22
    schen
    1.22
    sted
    1.19
    sver
    1.18
    sı
    1.13
    Act Density 1.399%

    No Known Activations