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

    Neuronpedia

    INDEX
    Explanations

    terms related to biological measurements and health metrics

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

    negative correlations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    TestingModule
    -0.54
    RotationOrder
    -0.51
    UserScript
    -0.49
    دانشنامهٔ
    -0.49
     considérons
    -0.47
    consulté
    -0.45
    MeasureSpec
    -0.43
    ">//
    -0.43
    encodeWith
    -0.42
    viewDidLoad
    -0.41
    POSITIVE LOGITS
     tin
    0.42
     Dalai
    0.39
    xFFFF
    0.39
     дописавши
    0.38
    berts
    0.38
     coldest
    0.37
    hard
    0.36
     Tin
    0.36
    timeScale
    0.35
     TIN
    0.35
    Act Density 0.289%

    No Known Activations