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

    Neuronpedia

    INDEX
    Explanations

    possessive pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    卅
    -0.07
    Cantidad
    -0.07
    .Condition
    -0.07
     设
    -0.07
    ADOS
    -0.07
    滪
    -0.06
    gold
    -0.06
    -billion
    -0.06
    ӡ
    -0.06
    קט
    -0.06
    POSITIVE LOGITS
     sliding
    0.07
     الفنان
    0.07
     analytic
    0.07
     clums
    0.07
    นะ
    0.07
     with
    0.07
    ביל
    0.07
     quận
    0.07
     prestige
    0.06
     Além
    0.06
    Act Density 0.037%

    No Known Activations