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

    Neuronpedia

    INDEX
    Explanations

    phrases related to scientific research and technical specifications

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

    measurement, date, or scientific context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Rujuakan
    -0.52
    Viited
    -0.46
    PostInfinity
    -0.45
     Numerade
    -0.45
    webElementGuid
    -0.39
    Notae
    -0.39
     createSlice
    -0.39
    ⟭
    -0.39
     CommonModule
    -0.38
    脚注の使い方
    -0.38
    POSITIVE LOGITS
    Parti
    0.46
    ⓘ
    0.43
    ⓧ
    0.41
    complexContent
    0.39
     Wikispecies
    0.38
    campal
    0.38
    Tazama
    0.38
    inguém
    0.36
    ConstraintMaker
    0.36
     Züge
    0.35
    Act Density 0.053%

    No Known Activations