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

    Neuronpedia

    INDEX
    Explanations

    forward motion

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    god
    -0.06
    .filename
    -0.06
    imité
    -0.06
     rac
    -0.06
    _BG
    -0.06
    ког
    -0.06
     Hurt
    -0.06
    supply
    -0.06
    ducation
    -0.06
    wan
    -0.06
    POSITIVE LOGITS
     Lawyer
    0.08
    Exercise
    0.07
     bla
    0.06
    >
    0.06
     shove
    0.06
    ΄
    0.06
    ./
    0.06
    []{"
    0.06
    :YES
    0.06
     article
    0.06
    Act Density 0.013%

    No Known Activations