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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     continent
    -0.07
    friends
    -0.07
    ایر
    -0.06
    络
    -0.06
    avoid
    -0.06
    (top
    -0.06
     jackpot
    -0.06
     roulette
    -0.06
     сад
    -0.06
     nar
    -0.06
    POSITIVE LOGITS
     『
    0.07
    έ
    0.07
     sns
    0.07
     hep
    0.06
    $config
    0.06
     demanded
    0.06
     kullanılan
    0.06
    ζα
    0.06
    	uint
    0.06
    	using
    0.06
    Act Density 0.000%

    No Known Activations