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

    Neuronpedia

    INDEX
    Explanations

    references to devices and data serialization in programming contexts

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

    start of turn user

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     resourceCulture
    -0.75
     defaultstate
    -0.72
     kasarigan
    -0.66
    routeProvider
    -0.62
    RuleContext
    -0.62
     propOrder
    -0.60
    berdayakan
    -0.60
    providedIn
    -0.59
     '\\;'
    -0.59
    ResponseWriter
    -0.56
    POSITIVE LOGITS
     ActivatedRoute
    1.63
    ↗
    0.89
    ↘
    0.86
    Retention
    0.61
     Deserialize
    0.53
     Retention
    0.52
     retention
    0.51
     torchvision
    0.46
    pulumi
    0.46
    ⇌
    0.41
    Act Density 0.000%

    No Known Activations