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

    Neuronpedia

    INDEX
    Explanations

    Gemini models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    சம்
    0.90
    截至
    0.88
    在
    0.87
    וריה
    0.87
    其
    0.84
     naman
    0.83
     cDNA
    0.83
    ereo
    0.83
     TeV
    0.83
    済
    0.82
    POSITIVE LOGITS
    o
    1.09
    𝒏
    1.02
    此之外
    1.00
     nhớ
    0.99
    ો
    0.99
    CMAKE
    0.98
     functor
    0.98
    ו
    0.97
     щодо
    0.97
    ه
    0.96
    Act Density 0.005%

    No Known Activations