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

    Neuronpedia

    INDEX
    Explanations

    sequences of punctuation or ellipses indicating pauses or omissions in text

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

    special mathematical expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    
    -0.55
     arşivlendi
    -0.52
    tagHelperRunner
    -0.50
     StringTokenizer
    -0.49
    #
    -0.49
    er
    -0.48
     Smar
    -0.46
    Smar
    -0.45
    ergic
    -0.44
     referrerpolicy
    -0.44
    POSITIVE LOGITS
    …………………………………………
    0.88
    …………
    0.76
    ………
    0.75
    ……………………
    0.75
    ………………………………
    0.73
    ……
    0.69
    ………………
    0.68
    ——————
    0.66
    ………..
    0.66
    ————
    0.65
    Act Density 0.009%

    No Known Activations