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

    Neuronpedia

    INDEX
    Explanations

    Possessive/personal pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
     declines
    -0.07
    вин
    -0.07
    .we
    -0.07
     toutes
    -0.07
    Duplicates
    -0.07
     AGAIN
    -0.06
     nå
    -0.06
     SIZE
    -0.06
    )y
    -0.06
    POSITIVE LOGITS
     crypt
    0.08
    棽
    0.07
     lief
    0.07
    ทา
    0.07
    🏢
    0.07
    utc
    0.07
    🍴
    0.07
    ϟ
    0.07
    مال
    0.07
    來自
    0.07
    Act Density 0.110%

    No Known Activations