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

    Neuronpedia

    INDEX
    Explanations

    stray

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nob
    -0.08
     счита
    -0.07
    \ORM
    -0.07
    Bio
    -0.07
    eygamber
    -0.06
     Zuk
    -0.06
    терес
    -0.06
    AnimationsModule
    -0.06
    upuncture
    -0.06
    uktur
    -0.06
    POSITIVE LOGITS
     stray
    0.16
    $update
    0.07
     err
    0.07
     slug
    0.07
     이
    0.07
    ay
    0.07
     tug
    0.06
     leftover
    0.06
     runaway
    0.06
     vag
    0.06
    Act Density 0.002%

    No Known Activations