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

    Neuronpedia

    INDEX
    Explanations

    with

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Answer
    -0.07
     dever
    -0.06
    нули
    -0.06
    _TIMEOUT
    -0.06
     CONTROL
    -0.06
     OVERRIDE
    -0.06
    ках
    -0.06
    oriented
    -0.06
     Sunset
    -0.06
     tutto
    -0.06
    POSITIVE LOGITS
    дин
    0.07
    zs
    0.06
     Bat
    0.06
    _dn
    0.06
    :";
↵
    0.06
     анализ
    0.06
     Mort
    0.06
    .xaxis
    0.06
     Resp
    0.06
    0.06
    Act Density 0.018%

    No Known Activations