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

    Neuronpedia

    INDEX
    Explanations

    Special events

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Fahrenheit
    -0.07
     tents
    -0.07
    Bond
    -0.07
     inplace
    -0.06
    =event
    -0.06
    .jwt
    -0.06
     Nim
    -0.06
    Jordan
    -0.06
    -foot
    -0.06
    RenderWindow
    -0.06
    POSITIVE LOGITS
    ̣
    0.07
    言い
    0.07
     persu
    0.06
    uron
    0.06
    success
    0.06
    ‑
    0.06
    884
    0.06
     Св
    0.06
     Portuguese
    0.06
    وجد
    0.06
    Act Density 0.009%

    No Known Activations