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

    Neuronpedia

    INDEX
    Explanations

    non-english characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    น่า
    1.02
    นี่
    1.02
    น
    0.99
    taro
    0.97
     telah
    0.96
     Productos
    0.96
    dır
    0.96
     Menteri
    0.95
     społec
    0.93
    იან
    0.92
    POSITIVE LOGITS
    ل
    1.16
    ны
    1.16
    ला
    1.14
    og
    1.13
    га
    1.08
    на
    1.05
    스
    1.05
    嗮
    1.01
    िस
    1.00
    сний
    0.99
    Act Density 0.000%

    No Known Activations