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

    Neuronpedia

    INDEX
    Explanations

    phrases indicating evaluation or assessment of experiences and performances

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

    most compelling, ideas, or moments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    kaŭ
    -0.46
    VersionUID
    -0.41
    getWriter
    -0.39
    RenderAtEndOf
    -0.38
     otomatig
    -0.37
    glBindBuffer
    -0.37
    findpost
    -0.36
    templateUrl
    -0.36
     مرئيه
    -0.35
    تقاوى
    -0.35
    POSITIVE LOGITS
    Източници
    0.55
    الحياه
    0.52
    AnchorTagHelper
    0.47
     geho
    0.47
     hardest
    0.45
     poorest
    0.45
     voors
    0.45
    InSection
    0.42
     najm
    0.42
    SequentialGroup
    0.41
    Act Density 0.075%

    No Known Activations