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

    Neuronpedia

    INDEX
    Explanations

    substitution or comparison

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     kingdom
    -0.07
     Guarantee
    -0.06
     Flying
    -0.06
     downwards
    -0.06
    궁
    -0.06
    альних
    -0.06
     إذ
    -0.06
     Fon
    -0.06
    lijah
    -0.06
    	group
    -0.06
    POSITIVE LOGITS
    もし
    0.07
    (ac
    0.07
     
    0.07
    녕하세요
    0.07
    ahaha
    0.07
    (),'
    0.06
     readable
    0.06
    _IE
    0.06
    (gr
    0.06
     Chicken
    0.06
    Act Density 0.043%

    No Known Activations