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

    Neuronpedia

    INDEX
    Explanations

    scientific human subject studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    真的
    -0.07
    ura
    -0.06
    ;?>
    -0.06
    NA
    -0.06
     sau
    -0.06
    PC
    -0.06
     lur
    -0.06
     t�
    -0.06
    ivers
    -0.06
    ians
    -0.06
    POSITIVE LOGITS
    ιλ
    0.07
     πραγμα
    0.07
    พย
    0.06
     درمان
    0.06
    ldb
    0.06
     █████
    0.06
    ToLeft
    0.06
    联盟
    0.06
    ительной
    0.06
     dissip
    0.06
    Act Density 0.021%

    No Known Activations