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

    Neuronpedia

    INDEX
    Explanations

    Pun

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Stephan
    -0.08
    ้แก
    -0.07
    �체
    -0.07
    ary
    -0.07
     phí
    -0.07
     Tess
    -0.07
    _ci
    -0.06
    ilee
    -0.06
     زمینه
    -0.06
    (slice
    -0.06
    POSITIVE LOGITS
     punished
    0.08
     Pun
    0.07
     punishment
    0.07
     punish
    0.07
     pun
    0.07
     支
    0.07
     лечения
    0.07
     Rosenstein
    0.07
     upon
    0.06
     непри
    0.06
    Act Density 0.006%

    No Known Activations