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

    Neuronpedia

    INDEX
    Explanations

    terms related to performance measurement in GPU architectures

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

    Code snippets with "max" or "best"

    np_acts-logits-general · gemini-2.0-flash

    maximum bounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    getTarget
    -0.49
     effect
    -0.43
    Blend
    -0.41
     resten
    -0.40
    เร็
    -0.40
    Target
    -0.40
     effects
    -0.39
     Stampa
    -0.39
    бно
    -0.39
     part
    -0.39
    POSITIVE LOGITS
    AndEndTag
    0.94
    ThroughAttribute
    0.88
    sizeCache
    0.86
     maxValue
    0.86
    RetentionPolicy
    0.78
     defaultstate
    0.77
     resourceCulture
    0.77
     BrowserModule
    0.75
     max
    0.75
    sidemargin
    0.74
    Act Density 0.346%

    No Known Activations