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

    Neuronpedia

    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    舞
    -0.06
     interact
    -0.06
     stitched
    -0.06
    KeyEvent
    -0.06
     숙
    -0.06
    enské
    -0.06
    циях
    -0.06
     sabah
    -0.06
     Cancel
    -0.05
     нек
    -0.05
    POSITIVE LOGITS
    ISING
    0.07
    ROTO
    0.07
     slov
    0.07
    صر
    0.07
     Charl
    0.07
     comprehensive
    0.06
    .mm
    0.06
     Commentary
    0.06
     Cond
    0.06
     Zurich
    0.06
    Act Density 0.071%

    No Known Activations