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

    Neuronpedia

    INDEX
    Explanations

    diverse document snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    िसक
    -0.07
     Loft
    -0.06
    Uid
    -0.06
    ?><
    -0.06
    оту
    -0.06
     provision
    -0.06
     ilan
    -0.06
    がない
    -0.06
     추천
    -0.06
    손
    -0.06
    POSITIVE LOGITS
    vement
    0.07
     hiệu
    0.06
     Jazeera
    0.06
     youths
    0.06
     meisjes
    0.06
     Tay
    0.06
     Scalia
    0.06
    เตอร
    0.06
    隊
    0.06
     Tray
    0.06
    Act Density 0.000%

    No Known Activations