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

    Neuronpedia

    INDEX
    Explanations

    say in-text citations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     showcasing
    -0.07
    -0.07
     môi
    -0.07
    מחו
    -0.07
                                    ↵
    -0.07
     ANSW
    -0.07
    感情
    -0.07
     nurture
    -0.07
    游戏装备
    -0.07
    禀
    -0.07
    POSITIVE LOGITS
    Square
    0.07
     scraped
    0.06
    -ajax
    0.06
     Dare
    0.06
    oser
    0.06
    .getStatus
    0.06
    Several
    0.06
    /z
    0.06
     several
    0.06
    -q
    0.06
    Act Density 0.045%

    No Known Activations