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

    Neuronpedia

    INDEX
    Explanations

    zero

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     volupt
    -0.06
     labyrinth
    -0.06
    CLOSE
    -0.06
    apl
    -0.06
    Laugh
    -0.06
    Movies
    -0.06
    tell
    -0.06
    ิจกรรม
    -0.05
     Maggie
    -0.05
     analiz
    -0.05
    POSITIVE LOGITS
    ेप
    0.07
    (svg
    0.07
     ruby
    0.07
     electrode
    0.06
     yerinde
    0.06
     slightest
    0.06
     Suzuki
    0.06
     روند
    0.06
    /nginx
    0.06
    0.06
    Act Density 0.002%

    No Known Activations