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

    Neuronpedia

    INDEX
    Explanations

    mathematical and code symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     apporte
    0.36
     มัน
    0.35
    ấ
    0.35
     egent
    0.34
     Cobb
    0.33
    [,
    0.33
    .
    0.33
    ))^
    0.32
     предоставляет
    0.32
     permette
    0.32
    POSITIVE LOGITS
    𝐟
    0.40
    וק
    0.39
    রাগ
    0.39
    ко
    0.39
     大
    0.38
    وار
    0.38
    وں
    0.38
    的大
    0.38
    uş
    0.37
    সি
    0.37
    Act Density 0.015%

    No Known Activations