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

    Neuronpedia

    INDEX
    Explanations

    summer months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    涮
    -0.07
    ⌵
    -0.07
    🕣
    -0.07
     notwithstanding
    -0.07
    edar
    -0.07
    ⏶
    -0.07
    שירה
    -0.06
    おすすめ
    -0.06
     undone
    -0.06
    小吃
    -0.06
    POSITIVE LOGITS
    _CIPHER
    0.07
     shells
    0.07
    (fig
    0.07
    Blo
    0.07
    .mass
    0.07
     Nil
    0.07
    RM
    0.07
    精确
    0.07
    /class
    0.07
    اسرائيل
    0.07
    Act Density 0.028%

    No Known Activations