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

    Neuronpedia

    INDEX
    Explanations

    parentheses and function-related syntax structures

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

    Code snippets or math formulas

    np_acts-logits-general · gemini-2.0-flash

    code delimiters and user input

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    transQ
    -1.09
    Datuak
    -0.89
    SharedCtor
    -0.86
    IsMutable
    -0.84
    LookAnd
    -0.84
    <unused41>
    -0.84
    <unused52>
    -0.84
    <unused17>
    -0.84
    <pad>
    -0.84
    <unused8>
    -0.84
    POSITIVE LOGITS
     is
    0.35
    Int
    0.32
    0
    0.31
     we
    0.30
    if
    0.29
     means
    0.29
    ?
    0.29
     were
    0.28
    1
    0.28
    :
    0.27
    Act Density 0.095%

    No Known Activations