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

    Neuronpedia

    INDEX
    Explanations

    Pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    سال
    -0.07
    Fast
    -0.07
     i
    -0.07
    固
    -0.06
    Bạn
    -0.06
     。
    -0.06
     posY
    -0.06
    Sans
    -0.06
    'utilisateur
    -0.06
     mange
    -0.06
    POSITIVE LOGITS
     initiating
    0.08
    _BOOLEAN
    0.07
     státu
    0.07
    .LayoutParams
    0.07
    생활
    0.06
    EF
    0.06
    iffe
    0.06
     instance
    0.06
    ponse
    0.06
    REFERENCE
    0.06
    Act Density 0.227%

    No Known Activations