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

    Neuronpedia

    INDEX
    Explanations

    Mid-1900s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     DL
    -0.07
    cert
    -0.07
    GL
    -0.07
    ]:↵↵
    -0.07
    AREN
    -0.07
    rk
    -0.07
    ometer
    -0.07
    'all
    -0.07
    하면서
    -0.06
     called
    -0.06
    POSITIVE LOGITS
     lưu
    0.07
    _episode
    0.06
     sû
    0.06
    ViewHolder
    0.06
    _EXEC
    0.06
     спортив
    0.06
     tailor
    0.06
     매우
    0.06
    :event
    0.06
    195
    0.06
    Act Density 0.037%

    No Known Activations