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

    Neuronpedia

    INDEX
    Explanations

    terms describing efficiency, effectiveness, and stability in various contexts

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

    Describes something as efficient or robust

    np_acts-logits-general · gemini-2.0-flash

    degree of sufficiency

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    #![
    -0.52
    LookAnd
    -0.51
    MLLoader
    -0.48
     препратки
    -0.46
     виправивши
    -0.46
    InputTagHelper
    -0.46
     BehaviorSubject
    -0.45
     <=",
    -0.42
     vVar
    -0.40
     getIs
    -0.40
    POSITIVE LOGITS
     enough
    1.05
    enough
    0.93
     Enough
    0.84
     ביותר
    0.82
     genug
    0.82
    Enough
    0.81
     للغاية
    0.77
     ENOUGH
    0.75
    ness
    0.75
     genoeg
    0.70
    Act Density 1.475%

    No Known Activations