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

    Neuronpedia

    INDEX
    Explanations

    site

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    gz
    -0.06
    paces
    -0.06
     superficial
    -0.06
    spin
    -0.06
    紹
    -0.06
     hrá
    -0.06
    iates
    -0.06
     //--------------------------------
    -0.06
    ầng
    -0.06
    capability
    -0.06
    POSITIVE LOGITS
    [array
    0.07
     Simulation
    0.07
    -binary
    0.06
    (tv
    0.06
    ศ
    0.06
    FileInfo
    0.06
    观看
    0.06
    .Clock
    0.06
     어떻게
    0.06
    TE
    0.06
    Act Density 0.005%

    No Known Activations