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

    Neuronpedia

    INDEX
    Explanations

    Recipes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     endeavour
    -0.08
     Lighting
    -0.07
    letter
    -0.07
     warehouse
    -0.07
    통
    -0.07
     wur
    -0.07
     infusion
    -0.07
    -li
    -0.07
     IEnumerable
    -0.06
     됩니다
    -0.06
    POSITIVE LOGITS
    (exit
    0.07
    WARDED
    0.07
    _STYLE
    0.06
    _done
    0.06
     yardımcı
    0.06
     구조
    0.06
    attro
    0.06
     {?}
    0.06
    ）。↵↵
    0.06
     exhibiting
    0.06
    Act Density 0.040%

    No Known Activations