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

    Neuronpedia

    INDEX
    Explanations

    final

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    まず
    -0.07
    ная
    -0.06
    재
    -0.06
    Approx
    -0.06
     Trav
    -0.06
    .system
    -0.06
    制造
    -0.06
    OUSE
    -0.06
    ्रय
    -0.06
     Gesture
    -0.06
    POSITIVE LOGITS
     floppy
    0.07
     fine
    0.07
     late
    0.07
     Cl
    0.07
     rest
    0.06
     final
    0.06
     dac
    0.06
     limb
    0.06
     Ep
    0.06
    064
    0.06
    Act Density 0.001%

    No Known Activations