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

    Neuronpedia

    INDEX
    Explanations

    Determinants and "the"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fou
    -0.29
    æĦĪ
    -0.29
    HTTP
    -0.27
    Integer
    -0.26
    nov
    -0.26
     locks
    -0.26
    æķ´
    -0.26
    没æĶ¶
    -0.25
    CLI
    -0.25
    å·®çĤ¹
    -0.24
    POSITIVE LOGITS
    aidu
    0.29
    /documents
    0.27
    çĻ½æĸij
    0.25
    æĸij
    0.25
    éĹ»è¨Ģ
    0.25
    ecake
    0.24
    æݨå¼Ģ
    0.24
    outed
    0.24
    naires
    0.24
     lesbians
    0.23
    Act Density 2.462%

    No Known Activations