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

    Neuronpedia

    INDEX
    Explanations

    XHTML

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    🇲
    -0.07
     Super
    -0.07
    줘
    -0.07
    良く
    -0.07
    _panel
    -0.07
     создания
    -0.07
    े
    -0.07
    .cmb
    -0.07
     minY
    -0.07
     fileprivate
    -0.07
    POSITIVE LOGITS
    -names
    0.08
    异议
    0.07
    =["
    0.07
    "):
↵
    0.07
     Author
    0.07
     Lecture
    0.07
    上看
    0.07
     Actions
    0.07
    指
    0.07
    [int
    0.07
    Act Density 0.001%

    No Known Activations