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

    Neuronpedia

    INDEX
    Explanations

    options, markets, lost opportunity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    یان
    1.29
    re
    1.22
    in
    1.18
     пожалуйста
    1.13
    inata
    1.11
    wert
    1.11
     والاست
    1.11
     Obrigado
    1.08
    -\
    1.08
     Expect
    1.06
    POSITIVE LOGITS
     separators
    1.34
    𝑟
    1.23
    ླ
    1.20
    riwal
    1.20
    ρθ
    1.16
    መሳሳይ
    1.13
    DOMstrings
    1.12
     মানসিক
    1.11
     NADPH
    1.11
    顾问
    1.11
    Act Density 0.000%

    No Known Activations