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

    Neuronpedia

    INDEX
    Explanations

    notational elements and mathematical expressions

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

    Bold font marker

    np_acts-logits-general · gemini-2.0-flash

    mathematical vectors and variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     larmes
    -0.70
    MethodManager
    -0.65
    riched
    -0.64
    FunctionFlags
    -0.62
     Sprung
    -0.61
     bezeichneter
    -0.60
     Prim
    -0.59
    tabular
    -0.59
     recevrez
    -0.59
    AsUp
    -0.58
    POSITIVE LOGITS
    mathbf
    0.86
    :+:
    0.59
     vectors
    0.56
    ARGB
    0.56
     Dvor
    0.55
     uninsured
    0.54
    Patterns
    0.53
    Демографія
    0.52
     IActionResult
    0.52
     harden
    0.52
    Act Density 0.389%

    No Known Activations