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

    Neuronpedia

    INDEX
    Explanations

    more

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Cutter
    -0.08
    (thing
    -0.07
    elem
    -0.07
     onStart
    -0.07
    ={(
    -0.07
    겋
    -0.07
     чуть
    -0.07
    菲尔
    -0.07
    (pts
    -0.07
    (hit
    -0.07
    POSITIVE LOGITS
    pir
    0.08
    各
    0.07
    𝙉
    0.07
    𝙡
    0.07
    各县
    0.07
    ﻜ
    0.07
     lower
    0.06
    醛
    0.06
     Guill
    0.06
     and
    0.06
    Act Density 0.005%

    No Known Activations