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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     역시
    -0.07
     parasite
    -0.07
    ament
    -0.06
     Maker
    -0.06
     rằng
    -0.06
     clones
    -0.06
     costo
    -0.06
     gran
    -0.06
     pong
    -0.06
     fung
    -0.06
    POSITIVE LOGITS
     essence
    0.06
     armor
    0.06
    ellschaft
    0.06
     Ecc
    0.06
    都不
    0.06
    (AF
    0.06
     incentiv
    0.06
     out
    0.06
    نش
    0.06
    _COMPLETED
    0.06
    Act Density 0.014%

    No Known Activations