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
     putas
    -0.07
    .API
    -0.07
     evet
    -0.06
    Reverse
    -0.06
     melodies
    -0.06
    .Lo
    -0.06
    꾸
    -0.06
    _QUERY
    -0.06
    meet
    -0.06
    .connect
    -0.06
    POSITIVE LOGITS
     физ
    0.07
     dressing
    0.07
     QQ
    0.06
     때문
    0.06
    relations
    0.06
    روت
    0.06
    INO
    0.06
     Dữ
    0.06
    킹
    0.06
     telah
    0.06
    Act Density 0.001%

    No Known Activations