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

    Neuronpedia

    INDEX
    Explanations

    perfect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     main
    -0.07
     bee
    -0.07
     clave
    -0.07
     bure
    -0.07
    -fly
    -0.07
     dro
    -0.06
    -day
    -0.06
    redential
    -0.06
    _SYS
    -0.06
     groups
    -0.06
    POSITIVE LOGITS
     perfect
    0.22
     Perfect
    0.19
    Perfect
    0.17
    perfect
    0.15
     perfectly
    0.14
     PERF
    0.10
     perfection
    0.10
     perfected
    0.09
     naprost
    0.08
    ECT
    0.08
    Act Density 0.012%

    No Known Activations