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

    Neuronpedia

    INDEX
    Explanations

    Warning

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Guess
    -0.07
    Point
    -0.07
    �
    -0.07
    Listener
    -0.07
    change
    -0.07
    不断提升
    -0.07
     mem
    -0.06
     Essence
    -0.06
    很清楚
    -0.06
    dependence
    -0.06
    POSITIVE LOGITS
     سنة
    0.08
    标准化
    0.08
    .public
    0.07
     daytime
    0.07
    uncios
    0.07
    akeFromNib
    0.07
    .modify
    0.07
    menus
    0.07
    iguiente
    0.07
    "/>↵↵
    0.07
    Act Density 0.005%

    No Known Activations