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

    Neuronpedia

    INDEX
    Explanations

    Non-English, code, and symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     הרח
    -0.08
     Bid
    -0.08
     Outlet
    -0.08
     quieren
    -0.08
     Long
    -0.08
     sightseeing
    -0.08
     בדר
    -0.07
     homelessness
    -0.07
    ‍ക്ക
    -0.07
     divided
    -0.07
    POSITIVE LOGITS
     beep
    0.11
     réussir
    0.10
     réuss
    0.09
     crisp
    0.09
     Erfolg
    0.09
     successes
    0.09
     सफलता
    0.09
    .wav
    0.09
     success
    0.09
     notifications
    0.09
    Act Density 0.024%

    No Known Activations