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

    Neuronpedia

    INDEX
    Explanations

    upgrade

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     被
    -0.07
     재
    -0.07
     bean
    -0.06
    \_
    -0.06
     starvation
    -0.06
     způsobem
    -0.06
     weaker
    -0.06
    Continuous
    -0.06
     řadu
    -0.06
     thorough
    -0.06
    POSITIVE LOGITS
    �체
    0.07
     Victorian
    0.07
     sparking
    0.06
    osp
    0.06
     GMC
    0.06
     descend
    0.06
    earable
    0.06
     строки
    0.06
     genç
    0.06
     Kew
    0.06
    Act Density 0.000%

    No Known Activations