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

    Neuronpedia

    INDEX
    Explanations

    strong

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    柄
    -0.07
    _ports
    -0.07
    angement
    -0.07
     lâu
    -0.07
    uffman
    -0.06
    =""><
    -0.06
     deutschen
    -0.06
     turbo
    -0.06
     Test
    -0.06
     Cros
    -0.06
    POSITIVE LOGITS
     strong
    0.08
     Em
    0.07
    toMatchSnapshot
    0.07
    报名
    0.06
    CE
    0.06
    jed
    0.06
     Personality
    0.06
     ALSO
    0.06
    844
    0.06
    (priority
    0.06
    Act Density 0.020%

    No Known Activations