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

    Neuronpedia

    INDEX
    Explanations

    Category

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    icide
    -0.07
     depois
    -0.07
     Death
    -0.07
    .management
    -0.07
    :H
    -0.06
    倒
    -0.06
     softly
    -0.06
    	RT
    -0.06
    慢
    -0.06
     قرار
    -0.06
    POSITIVE LOGITS
    %"↵
    0.06
     cocktails
    0.06
     flav
    0.06
     Yong
    0.06
     artisan
    0.06
    Dragon
    0.06
     NBA
    0.06
     trivia
    0.06
     برگ
    0.06
     Голов
    0.05
    Act Density 0.008%

    No Known Activations