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

    Neuronpedia

    INDEX
    Explanations

    instances of mathematical symbols and programming constructs

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

    Precedes punctuation or symbols

    np_acts-logits-general · gemini-2.0-flash

    punctuation and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "},
    -0.56
    Spoljašnje
    -0.51
     ‪
    -0.51
    \""
    -0.50
    ประก
    -0.49
     fuper
    -0.49
     Thon
    -0.48
    bá
    -0.48
     bewer
    -0.48
    entieth
    -0.47
    POSITIVE LOGITS
    MENAFN
    0.78
    
    0.75
     Gallimard
    0.59
     T
    0.58
    tvguidetime
    0.57
    endphp
    0.56
    T
    0.55
    Silva
    0.54
     M
    0.53
     الحره
    0.53
    Act Density 0.990%

    No Known Activations