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

    Neuronpedia

    INDEX
    Explanations

    scientific notations and mathematical expressions

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

    "E" followed by a plus sign

    np_acts-logits-general · gemini-2.0-flash

    scientific notation E+ followed by plus

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     referrerpolicy
    -0.45
     fences
    -0.41
     mã
    -0.39
    LabelTagHelper
    -0.38
     judges
    -0.38
     judgements
    -0.35
     judge
    -0.34
     prisons
    -0.34
     iprot
    -0.34
     jugement
    -0.34
    POSITIVE LOGITS
    Tikang
    0.49
    writeField
    0.48
    Portale
    0.47
    pplung
    0.46
     maux
    0.44
    ViewById
    0.44
     MotionEvent
    0.43
    prüche
    0.43
    يكب
    0.42
     newInstance
    0.42
    Act Density 0.311%

    No Known Activations