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

    Neuronpedia

    INDEX
    Explanations

    expressions of uncertainty or tentativeness in statements

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

    express states or opinions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     outta
    -0.68
     Aussie
    -0.57
     gonna
    -0.54
     wanna
    -0.50
     gotta
    -0.49
    Aussie
    -0.48
     اون
    -0.47
     sorta
    -0.46
     somethin
    -0.45
     fuckin
    -0.45
    POSITIVE LOGITS
    uxxxx
    0.79
    mektedir
    0.68
    maktadır
    0.61
    EndInit
    0.58
    autoreleasepool
    0.57
     skall
    0.56
    cektir
    0.54
     입니다
    0.54
    rungsseite
    0.53
    __;
    0.51
    Act Density 0.378%

    No Known Activations