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

    Neuronpedia

    INDEX
    Explanations

    source code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _KeyPress
    -0.08
     срок
    -0.07
    摇了摇头
    -0.07
     complaining
    -0.07
    ]")
    -0.07
     Semantic
    -0.06
    def
    -0.06
     sparing
    -0.06
    תחר
    -0.06
    죔
    -0.06
    POSITIVE LOGITS
    高新
    0.07
     Süd
    0.07
    迪拜
    0.07
    _training
    0.06
    itat
    0.06
     SQ
    0.06
     NYT
    0.06
    輛
    0.06
     Increased
    0.06
    /environment
    0.06
    Act Density 0.113%

    No Known Activations