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

    Neuronpedia

    INDEX
    Explanations

    numbers followed by units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    つ
    0.71
    つの
    0.71
     つ
    0.67
     дву
    0.64
    らん
    0.64
    -'].
    0.63
    ಡ
    0.63
     më
    0.63
    д
    0.62
     diagonally
    0.62
    POSITIVE LOGITS
     MINUTES
    0.91
     nationalities
    0.90
     percent
    0.90
    传媒
    0.90
     minutes
    0.85
    %
    0.84
     nations
    0.82
    শে
    0.81
     countries
    0.79
     тысяч
    0.79
    Act Density 0.154%

    No Known Activations