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

    Neuronpedia

    INDEX
    Explanations

    know this

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    2.09
     equate
    2.08
    िया
    1.97
    मीटर
    1.88
    та
    1.86
    ذا
    1.83
    のを
    1.79
    𝐡
    1.77
    گ
    1.76
    𝐰
    1.74
    POSITIVE LOGITS
    an
    1.96
    ist
    1.89
     bioavailability
    1.88
    dür
    1.87
     ग्रस्त
    1.86
     poisoning
    1.83
    roits
    1.80
    Decre
    1.80
    LowerCase
    1.77
     ulcers
    1.77
    Act Density 0.080%

    No Known Activations