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

    Neuronpedia

    INDEX
    Explanations

    numbers and units like kg, percent, ratio

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    am
    1.00
    e
    0.92
    i
    0.84
    en
    0.84
    \,.
    0.79
     Raghav
    0.77
    el
    0.77
    ebay
    0.76
    yad
    0.76
    ROBERT
    0.76
    POSITIVE LOGITS
    鳧
    0.73
     ενός
    0.73
    த்தில்
    0.72
    할
    0.71
    ının
    0.70
    에서는
    0.69
    ية
    0.68
    じ
    0.68
    하는
    0.67
    小時
    0.67
    Act Density 0.002%

    No Known Activations