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

    Neuronpedia

    INDEX
    Explanations

    First/second person pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ündeki
    -0.07
    вания
    -0.06
    cean
    -0.06
     поверхность
    -0.06
    stre
    -0.06
     Sleeve
    -0.06
     Avenue
    -0.06
     문의
    -0.06
    060
    -0.06
     Una
    -0.06
    POSITIVE LOGITS
    πο
    0.08
     pounding
    0.07
    *Math
    0.07
    earable
    0.07
    umatic
    0.06
    UTOR
    0.06
     stronghold
    0.06
    emonic
    0.06
    emble
    0.06
     pled
    0.06
    Act Density 0.053%

    No Known Activations