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

    Neuronpedia

    INDEX
    Explanations

    code, paths, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     रखना
    -0.09
    Absolutely
    -0.08
     रखने
    -0.08
     HY
    -0.08
     definitivamente
    -0.08
     علينا
    -0.07
    (emp
    -0.07
    Estim
    -0.07
     Absolutely
    -0.07
    tal
    -0.07
    POSITIVE LOGITS
    ]↵↵
    0.08
     Contin
    0.08
    ]
↵
↵
    0.08
     continues
    0.07
     leisurely
    0.07
     infinitely
    0.07
    在线视频
    0.07
     paused
    0.07
    ]↵//
    0.07
     compressed
    0.07
    Act Density 0.000%

    No Known Activations