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

    Neuronpedia

    INDEX
    Explanations

    sharp

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (ms
    -0.07
    ________
    -0.07
     женщина
    -0.07
    spa
    -0.06
    /input
    -0.06
     �
    -0.06
    _adv
    -0.06
    epam
    -0.06
     sheets
    -0.06
     ча
    -0.06
    POSITIVE LOGITS
     sharper
    0.11
     pointed
    0.07
     corrosion
    0.07
     Rif
    0.07
    Pressed
    0.07
    Unless
    0.06
     onder
    0.06
    .toolStripMenuItem
    0.06
    -trigger
    0.06
     militant
    0.06
    Act Density 0.024%

    No Known Activations