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
    volume
    -0.07
    มา
    -0.07
     ideal
    -0.07
    anti
    -0.07
     ▲
    -0.06
     recuper
    -0.06
    pus
    -0.06
    errar
    -0.06
    ruž
    -0.06
    uploads
    -0.06
    POSITIVE LOGITS
     activations
    0.07
     ValueEventListener
    0.07
     congressman
    0.06
    Means
    0.06
     розта
    0.06
    ่ต
    0.06
    .They
    0.06
     they
    0.06
     uniqueness
    0.06
     선택
    0.06
    Act Density 0.019%

    No Known Activations