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

    Neuronpedia

    INDEX
    Explanations

    names of television personalities and hosts

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

    people's names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kasarigan
    -0.50
    endfor
    -0.32
    ("../
    -0.32
    šė
    -0.31
     들
    -0.30
     حفظ
    -0.29
    stā
    -0.29
    ("../../
    -0.29
     Blau
    -0.29
    CloseHandle
    -0.29
    POSITIVE LOGITS
    rrggbb
    0.65
    Jereo
    0.63
    CloseOperation
    0.59
    ंदीखरीदारी
    0.56
     betweenstory
    0.55
    parsedMessage
    0.54
    matchCondition
    0.54
    хьтан
    0.51
    typeorm
    0.50
    səhifə
    0.50
    Act Density 0.022%

    No Known Activations