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

    Neuronpedia

    INDEX
    Explanations

    names of months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     R
    0.47
    USAGE
    0.45
    國
    0.44
    R
    0.43
     Sor
    0.42
     ಶಾ
    0.42
     Sab
    0.42
     Newell
    0.42
     Duran
    0.42
    ZV
    0.42
    POSITIVE LOGITS
    <0xA0>
    0.50
     février
    0.48
     fevereiro
    0.46
     فبراير
    0.46
     Bootstrap
    0.46
    푚
    0.46
     bootstra
    0.45
    \</
    0.44
     Тыва
    0.43
    ～。
    0.43
    Act Density 0.002%

    No Known Activations