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

    Neuronpedia

    INDEX
    Explanations

    should

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     फल
    -0.08
     حيث
    -0.08
     sinh
    -0.07
    ಕಾರಿ
    -0.07
    ಕಾರ
    -0.07
     ಕ
    -0.07
     Dungeon
    -0.07
    ...
↵
    -0.07
    urile
    -0.07
     heb
    -0.07
    POSITIVE LOGITS
     inoltre
    0.11
     außerdem
    0.09
     Besonder
    0.09
     remuneration
    0.09
     соблюдать
    0.09
     enfin
    0.09
     итоге
    0.08
     certification
    0.08
     Certification
    0.08
     помнить
    0.08
    Act Density 0.033%

    No Known Activations