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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and structure elements

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

    Conditionals, especially checking for inequality

    np_acts-logits-general · gemini-2.0-flash

    negation in conditional statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     تضيفلها
    -0.89
    GraphicsUnit
    -0.88
    AndEndTag
    -0.86
    ConstraintMaker
    -0.85
     silence
    -0.80
     Silence
    -0.79
     EconPapers
    -0.76
     ujednoznacz
    -0.76
    awtextra
    -0.75
     Waray
    -0.75
    POSITIVE LOGITS
     not
    1.10
     non
    1.06
     nicht
    1.03
     unsuitable
    1.01
     incorrect
    1.01
     не
    0.94
     improper
    0.93
    不
    0.93
     wrong
    0.92
     неправи
    0.92
    Act Density 0.802%

    No Known Activations