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

    Neuronpedia

    INDEX
    Explanations

    articles/pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     言
    -0.07
    eggies
    -0.07
    china
    -0.07
     spotify
    -0.07
     jedním
    -0.06
     insanın
    -0.06
     processing
    -0.06
    ân
    -0.06
     Doch
    -0.06
    ;c
    -0.06
    POSITIVE LOGITS
    htub
    0.06
    -------------</
    0.06
     बच
    0.06
     paní
    0.06
     unaffected
    0.06
     Đây
    0.06
    货
    0.05
    altimore
    0.05
     Pemb
    0.05
     learns
    0.05
    Act Density 0.177%

    No Known Activations