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

    Neuronpedia

    INDEX
    Explanations

    references to programming code or data structures

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

    mathematical expressions with punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ValueStyle
    -1.06
     CreateTagHelper
    -0.98
     المعيارى
    -0.85
     ModelExpression
    -0.84
     AssemblyTitle
    -0.83
    Personensuche
    -0.79
     endwhile
    -0.79
    原始内容存档于
    -0.79
    contentLoaded
    -0.76
    +:+
    -0.74
    POSITIVE LOGITS
     eer
    0.31
    cy
    0.30
    a
    0.29
    y
    0.29
     are
    0.29
    ism
    0.29
    t
    0.27
     s
    0.27
    c
    0.27
    NewUser
    0.27
    Act Density 0.066%

    No Known Activations