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

    Neuronpedia

    INDEX
    Explanations

    Interview transcripts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     médecin
    -0.07
    ề
    -0.07
    asan
    -0.07
     aloud
    -0.06
     addressed
    -0.06
    cio
    -0.06
    紧密
    -0.06
    ategoria
    -0.06
    Common
    -0.06
     doen
    -0.06
    POSITIVE LOGITS
    Mongo
    0.07
     cv
    0.07
    东方财富
    0.07
     lad
    0.07
     uncon
    0.06
     Hook
    0.06
    胞
    0.06
    ounty
    0.06
     Allied
    0.06
     字
    0.06
    Act Density 0.050%

    No Known Activations