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

    Neuronpedia

    INDEX
    Explanations

    Korean pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Substance
    -0.07
     dbContext
    -0.07
     separately
    -0.07
     Sanchez
    -0.07
     *=
    -0.07
     Phần
    -0.07
     lavoro
    -0.07
     nó
    -0.06
    روب
    -0.06
    parate
    -0.06
    POSITIVE LOGITS
     저
    0.15
    저
    0.10
     recommendation
    0.07
     Zheng
    0.07
    200
    0.07
    papers
    0.06
    rstrip
    0.06
     crit
    0.06
     trous
    0.06
     entered
    0.06
    Act Density 0.002%

    No Known Activations