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

    Neuronpedia

    INDEX
    Explanations

    exclamatory and emphasized expressions indicating strong emotions or reactions

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

    Repeated letters or characters

    np_acts-logits-general · gemini-2.0-flash

    elongated vowels and repeated symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    balleur
    -0.61
    存于互联网档案馆
    -0.59
    Datuak
    -0.56
    ện
    -0.52
    Fly
    -0.52
    ‌ی
    -0.51
    Mav
    -0.51
    Pax
    -0.50
    enzie
    -0.50
     trac
    -0.49
    POSITIVE LOGITS
    ooooo
    0.69
    !!!!!
    0.61
    !!!!
    0.61
    🔥🔥🔥
    0.60
    ?????
    0.59
    oooo
    0.59
     FFFF
    0.59
    rrrrr
    0.59
    oooooo
    0.59
     defStyleAttr
    0.59
    Act Density 0.590%

    No Known Activations