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

    Neuronpedia

    INDEX
    Explanations

    do

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Hydraulic
    -0.07
    陶
    -0.07
    iosity
    -0.06
     Wealth
    -0.06
    	where
    -0.06
    乗
    -0.06
     мов
    -0.06
     vomiting
    -0.06
    sek
    -0.06
     Preparation
    -0.06
    POSITIVE LOGITS
     honoring
    0.08
     Admir
    0.07
    arrants
    0.06
    (SQLException
    0.06
    、マ
    0.06
     권
    0.06
    (td
    0.06
    ()/
    0.06
    线
    0.06
     manga
    0.06
    Act Density 0.000%

    No Known Activations