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

    Neuronpedia

    INDEX
    Explanations

    micro

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Girl
    -0.07
     oils
    -0.07
    誉
    -0.07
     نصب
    -0.07
     пер
    -0.06
     Milky
    -0.06
     fragrance
    -0.06
     prosperous
    -0.06
    uma
    -0.06
     allergic
    -0.06
    POSITIVE LOGITS
     frost
    0.07
    τύ
    0.06
     investigators
    0.06
    pay
    0.06
    DbType
    0.06
    χος
    0.06
    ffield
    0.06
    stmt
    0.06
    ycl
    0.06
    χ
    0.06
    Act Density 0.008%

    No Known Activations