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

    Neuronpedia

    INDEX
    Explanations

    вы

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     biên
    -0.07
    ads
    -0.07
    redis
    -0.07
    Planning
    -0.07
    ubernetes
    -0.07
    سان
    -0.07
     […
    -0.07
     amen
    -0.06
     usuario
    -0.06
     Principal
    -0.06
    POSITIVE LOGITS
    snow
    0.08
     Snackbar
    0.07
     buflen
    0.07
    好看的
    0.07
    比例
    0.07
     Replacement
    0.07
     Rift
    0.07
    体现出
    0.07
    (exit
    0.07
    打出
    0.07
    Act Density 0.029%

    No Known Activations