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

    Neuronpedia

    INDEX
    Explanations

    LaTeX or mathematical expressions and notations

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

    LaTeX math and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AndEndTag
    -0.42
    rawDesc
    -0.40
    SequentialGroup
    -0.40
     esternos
    -0.36
    makeConstraints
    -0.36
    addCriterion
    -0.35
     setempat
    -0.35
     advertencia
    -0.35
     barnen
    -0.34
    TokenNameDOT
    -0.34
    POSITIVE LOGITS
    TokenName
    0.67
    istoitu
    0.59
    ˹
    0.54
    theoremstyle
    0.54
    @[+][
    0.53
    varargin
    0.52
     venons
    0.50
     varargin
    0.50
    protoimpl
    0.49
    principalTable
    0.49
    Act Density 0.346%

    No Known Activations