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

    Neuronpedia

    INDEX
    Explanations

    team

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     phenomenon
    -0.07
     Tarihi
    -0.07
    .__
    -0.07
     meio
    -0.06
    asında
    -0.06
    *w
    -0.06
     designing
    -0.06
    ycop
    -0.06
     benefited
    -0.06
    []
    -0.06
    POSITIVE LOGITS
    聞
    0.06
    PLUGIN
    0.06
    .Locale
    0.06
     NVIC
    0.06
     채용
    0.06
     сообщ
    0.06
    hor
    0.06
    	connection
    0.06
    "/>↵↵
    0.06
     ters
    0.06
    Act Density 0.000%

    No Known Activations