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

    Neuronpedia

    INDEX
    Explanations

    great

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ului
    -0.08
    \AppData
    -0.07
     pop
    -0.07
     Cumhuriyet
    -0.07
     easier
    -0.06
     spam
    -0.06
     onload
    -0.06
    _poly
    -0.06
     chess
    -0.06
    (Handle
    -0.06
    POSITIVE LOGITS
     بزر
    0.07
    (dirname
    0.07
     great
    0.07
    (sprite
    0.07
    _GATE
    0.06
    width
    0.06
    息
    0.06
     greatly
    0.06
    Ids
    0.06
    昇
    0.06
    Act Density 0.022%

    No Known Activations