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

    Neuronpedia

    INDEX
    Explanations

    the + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    1.19
    и
    1.16
     и
    1.15
    ık
    1.13
    ا
    1.12
    1.11
    ’
    1.09
    Dd
    1.05
    I
    1.05
     і
    1.02
    POSITIVE LOGITS
    सिल
    1.05
    針對
    1.03
     Europäischen
    1.02
     ສຳ
    1.01
     erklärte
    1.01
    叕
    1.00
    针对
    0.99
    ຜະລ
    0.98
     scourge
    0.98
    िया
    0.96
    Act Density 0.170%

    No Known Activations