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

    Neuronpedia

    INDEX
    Explanations

    references to specific variables and statistical data in programming or technical contexts

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

    DA sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ıyordu
    -0.34
    ukunft
    -0.32
     sfondo
    -0.32
     vores
    -0.30
     dalamnya
    -0.30
     piele
    -0.29
     частности
    -0.28
    ılmış
    -0.28
     zakład
    -0.28
    ⎩
    -0.28
    POSITIVE LOGITS
     IA
    0.68
     JA
    0.66
    tA
    0.65
     VA
    0.63
    rA
    0.63
     dA
    0.63
    cA
    0.63
    aA
    0.62
    VA
    0.62
    SA
    0.60
    Act Density 0.260%

    No Known Activations