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

    Neuronpedia

    INDEX
    Explanations

    single digits

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     plated
    -0.08
     مهم
    -0.07
     Bracket
    -0.07
     Expect
    -0.07
     Carn
    -0.07
    谶
    -0.06
    自治
    -0.06
    aciente
    -0.06
     delimited
    -0.06
     z
    -0.06
    POSITIVE LOGITS
     York
    0.07
     Orth
    0.07
     Liberty
    0.07
    ᅨ
    0.06
    XX
    0.06
    去年同期
    0.06
    URITY
    0.06
     RTBU
    0.06
    ∥
    0.06
    这两天
    0.06
    Act Density 0.011%

    No Known Activations