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

    Neuronpedia

    INDEX
    Explanations

    terms related to simplification and organization

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

    Requests to simplify expressions

    np_acts-logits-general · gemini-2.0-flash

    simplify expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    IBOutlet
    -0.55
    EPC
    -0.46
    قایناق‌لار
    -0.46
    JspWriter
    -0.45
    gsSP
    -0.44
     estekak
    -0.44
    tagext
    -0.43
    drawSprites
    -0.42
    LookAnd
    -0.41
    tinyos
    -0.41
    POSITIVE LOGITS
    simplify
    0.75
     simplify
    0.70
     Simplify
    0.66
     simplifying
    0.65
    simplified
    0.63
     simplified
    0.63
     simplification
    0.62
     globalization
    0.62
     simplif
    0.60
     simplifies
    0.60
    Act Density 0.558%

    No Known Activations