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

    Neuronpedia

    INDEX
    Explanations

    high-level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    사람
    1.23
    نت
    1.04
    Yet
    1.04
    っていない
    1.03
    ियत
    1.02
     insanların
    1.01
     beiden
    1.00
    人们
    0.99
    Shortly
    0.99
    ன
    0.98
    POSITIVE LOGITS
    V
    1.22
    T
    1.06
     technology
    1.02
     sided
    1.00
     aerospace
    0.97
     searing
    0.94
     Ordnance
    0.94
    ブリッド
    0.94
     eyewear
    0.93
     horsepower
    0.93
    Act Density 0.246%

    No Known Activations