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

    Neuronpedia

    INDEX
    Explanations

    language generation prompts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itm
    -0.08
    �
    -0.08
     selenium
    -0.07
    ,
    -0.07
    -center
    -0.07
     subst
    -0.07
     Selenium
    -0.07
     ECG
    -0.07
    -0.07
     Mohammad
    -0.07
    POSITIVE LOGITS
     لغة
    0.13
     язык
    0.12
     civilization
    0.12
     языке
    0.12
     языка
    0.12
     ഭാഷ
    0.12
     língua
    0.12
     langues
    0.12
     invented
    0.11
     langue
    0.11
    Act Density 0.030%

    No Known Activations