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

    Neuronpedia

    INDEX
    Explanations

    instances of opening parentheses and curly braces in code or expressions

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

    code structures or data maps

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "];
    -0.35
    󠁣
    -0.35
    l
    -0.35
    '));
    -0.34
    '].'
    -0.34
    л
    -0.33
    व
    -0.33
    ':
    -0.33
    ov
    -0.33
    "]="
    -0.32
    POSITIVE LOGITS
     ({
    0.99
     Carrasco
    0.64
    iſen
    0.63
     summarised
    0.62
    (({
    0.61
    ={({
    0.61
     &___
    0.61
     ${({
    0.60
    mechanism
    0.59
     Geſch
    0.58
    Act Density 0.002%

    No Known Activations