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

    Neuronpedia

    INDEX
    Explanations

    lecture

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    going
    -0.07
    .waitKey
    -0.06
    ++++++++++++++++++++++++++++++++
    -0.06
    .hash
    -0.06
    .getSession
    -0.06
     fellows
    -0.06
    ليه
    -0.06
     gamers
    -0.06
     плеч
    -0.06
     века
    -0.06
    POSITIVE LOGITS
     Connecticut
    0.07
     Malcolm
    0.06
    (false
    0.06
    Elf
    0.06
    .…↵↵
    0.06
    :h
    0.06
     paid
    0.06
     Fem
    0.06
    dür
    0.06
    bursement
    0.06
    Act Density 0.000%

    No Known Activations