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

    Neuronpedia

    INDEX
    Explanations

    carried

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     XML
    -0.07
     credible
    -0.07
    (hostname
    -0.06
    Ster
    -0.06
     spe
    -0.06
    Articles
    -0.06
    asthan
    -0.06
    (icon
    -0.06
     jednání
    -0.06
    (prop
    -0.06
    POSITIVE LOGITS
     tấm
    0.07
    ❤
    0.07
    كه
    0.07
    ξει
    0.06
     ♥
    0.06
    PLAY
    0.06
    ilded
    0.06
     dar
    0.06
     candies
    0.06
     ген
    0.06
    Act Density 0.005%

    No Known Activations