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

    Neuronpedia

    INDEX
    Explanations

    expressions of emotional discomfort or anxiety

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

    Follows a sentence-ending punctuation mark

    np_acts-logits-general · gemini-2.0-flash

    proteins associated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nahilalakip
    -0.95
     Roskov
    -0.87
    ^(@)
    -0.87
    verständlich
    -0.83
    <?
    -0.82
    StoryboardSegue
    -0.81
     iNdEx
    -0.78
     незавершена
    -0.77
     مشين
    -0.75
    новништво
    -0.73
    POSITIVE LOGITS
    Worse
    1.40
     Worse
    1.36
     Fortunately
    1.30
    Fortunately
    1.28
     Luckily
    1.15
    Luckily
    1.11
     worse
    1.09
     Thankfully
    1.06
    Thankfully
    1.04
    好在
    1.01
    Act Density 0.417%

    No Known Activations