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

    Neuronpedia

    INDEX
    Explanations

    Facade and CoinGecko

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ₁.
    0.70
    AR
    0.64
    izante
    0.61
    ᴀ
    0.61
    ISH
    0.61
    RICT
    0.59
    smittel
    0.58
    ے۔
    0.57
     зале
    0.57
    🛂
    0.57
    POSITIVE LOGITS
    '
    0.98
    /
    0.87
    ل
    0.87
    在
    0.87
    ’
    0.84
    ت
    0.79
    :
    0.77
    <0x0D>
    0.73
    </h2>
    0.72
    ש
    0.71
    Act Density 0.001%

    No Known Activations