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

    Neuronpedia

    INDEX
    Explanations

    0

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    럼
    -0.08
    =Y
    -0.08
    ':''
    -0.08
     Whatsapp
    -0.07
     ότι
    -0.07
     kB
    -0.07
     thép
    -0.07
    wishlist
    -0.07
    /avatar
    -0.06
    ﺘ
    -0.06
    POSITIVE LOGITS
    lerinin
    0.08
     HH
    0.07
    ({
    0.06
     Çin
    0.06
     AR
    0.06
    China
    0.06
    enda
    0.06
     CHE
    0.06
    	info
    0.06
     colonization
    0.06
    Act Density 0.011%

    No Known Activations