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

    Neuronpedia

    INDEX
    Explanations

    K : using

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Reak
    -0.82
     kuasa
    -0.81
    ၌
    -0.74
     hasilnya
    -0.74
     diharapkan
    -0.74
    lekt
    -0.73
     cherchez
    -0.73
    逡
    -0.73
    Consume
    -0.73
     Motive
    -0.71
    POSITIVE LOGITS
     erila
    0.77
     använd
    0.76
     OA
    0.75
    ジ
    0.75
     Else
    0.72
     پر
    0.72
    iori
    0.72
    0.71
     дочь
    0.71
    MUN
    0.71
    Act Density 0.003%

    No Known Activations