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

    Neuronpedia

    INDEX
    Explanations

    questions and answers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    referer
    -0.08
    роме
    -0.06
     बड
    -0.06
     گن
    -0.06
     мире
    -0.06
     Chelsea
    -0.06
    aturated
    -0.06
    aca
    -0.06
    지고
    -0.06
    	info
    -0.06
    POSITIVE LOGITS
    Past
    0.07
    remote
    0.06
    chn
    0.06
    <Key
    0.06
     منابع
    0.06
            
↵
↵
    0.06
    Ranges
    0.06
    _black
    0.06
     Nep
    0.06
    خذ
    0.06
    Act Density 0.066%

    No Known Activations