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

    Neuronpedia

    INDEX
    Explanations

    Hexadecimal constants

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    оры
    -0.07
     business
    -0.06
    .week
    -0.06
    人民
    -0.06
    __.__
    -0.06
    .menu
    -0.06
     felony
    -0.06
     Adjustment
    -0.06
     kẻ
    -0.06
    显示
    -0.06
    POSITIVE LOGITS
    Looks
    0.06
     elt
    0.06
     strongly
    0.06
    روع
    0.06
     aaa
    0.06
     screamed
    0.06
     zz
    0.06
    0.06
     LOL
    0.06
     figur
    0.06
    Act Density 0.006%

    No Known Activations