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

    Neuronpedia

    INDEX
    Explanations

    conditional expressions and logical comparisons in code

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

    Code comparing values

    np_acts-logits-general · gemini-2.0-flash

    programming code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     "
    -0.54
     “
    -0.49
    “
    -0.49
     is
    -0.49
    able
    -0.47
    ,
    -0.47
    "
    -0.47
    /
    -0.47
     if
    -0.46
    —
    -0.45
    POSITIVE LOGITS
    Geplaatst
    1.09
    CppMethod
    1.09
    writeFieldEnd
    1.04
    principalTable
    1.04
     تضيفلها
    0.99
     للاسماء
    0.98
    ValueStyle
    0.94
    verwijspagina
    0.90
    SharedDtor
    0.89
    abestanden
    0.89
    Act Density 0.064%

    No Known Activations