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

    Neuronpedia

    INDEX
    Explanations

    read more show

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     rooted
    -0.07
     McK
    -0.06
     racism
    -0.06
    —even
    -0.06
     Bingo
    -0.06
     ---↵
    -0.06
    �
    -0.06
     الشر
    -0.06
    icios
    -0.06
    responsive
    -0.06
    POSITIVE LOGITS
    Fd
    0.07
     увелич
    0.07
    UPI
    0.07
     chiar
    0.07
    لف
    0.06
     occup
    0.06
    .Bot
    0.06
    _WIDGET
    0.06
    	Context
    0.06
    -terminal
    0.06
    Act Density 0.169%

    No Known Activations