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

    Neuronpedia

    INDEX
    Explanations

    code commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sonoma
    -0.08
    ರೆದ
    -0.08
     careless
    -0.08
     Bola
    -0.08
     misunderstood
    -0.07
     MRT
    -0.07
     תה
    -0.07
     nightly
    -0.07
     incompetent
    -0.07
     Kana
    -0.07
    POSITIVE LOGITS
     realistically
    0.09
     сеп
    0.09
    оедин
    0.08
     realistic
    0.08
     മുഴ
    0.08
    Filtered
    0.08
     */,↵
    0.08
     **/↵
    0.07
     സന്ത
    0.07
    cher
    0.07
    Act Density 0.001%

    No Known Activations