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

    Neuronpedia

    INDEX
    Explanations

    positive outcome, attitude, experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _{[
    2.31
    بھ
    2.21
    }^{(
    2.15
    ington
    2.15
    raa
    2.06
    熬
    2.00
    첸
    1.99
    علم
    1.98
    antd
    1.98
    ตรฐาน
    1.98
    POSITIVE LOGITS
    /−
    3.17
    /+
    2.00
    gap
    1.95
     (+)
    1.94
    ྤ
    1.92
     penser
    1.92
     مقابل
    1.90
     ".
    1.86
    lette
    1.83
    ྒ
    1.83
    Act Density 0.338%

    No Known Activations