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

    Neuronpedia

    INDEX
    Explanations

    work, jobs, and tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    është
    0.45
    я
    0.45
    Я
    0.43
    V
    0.43
     najlepiej
    0.41
    ле
    0.41
    LE
    0.41
    ジャ
    0.41
    śli
    0.40
    ят
    0.40
    POSITIVE LOGITS
     recess
    0.49
     economia
    0.43
     eggplant
    0.43
     foldable
    0.41
     enqueue
    0.41
     deposito
    0.41
    ゝ
    0.40
     Guangzhou
    0.40
     Shandong
    0.40
     salario
    0.40
    Act Density 0.001%

    No Known Activations