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

    Neuronpedia

    INDEX
    Explanations

    november 2nd, 2023

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    EDY
    0.77
    ться
    0.75
     Elizabethan
    0.74
     Quillen
    0.71
     niche
    0.71
    тися
    0.70
    就算是
    0.70
    iyu
    0.70
    ukti
    0.70
    entu
    0.70
    POSITIVE LOGITS
    9
    0.96
    8
    0.95
    6
    0.91
    7
    0.90
    3
    0.89
    4
    0.85
     කොට
    0.79
    SCO
    0.75
    5
    0.72
    اخ
    0.69
    Act Density 0.030%

    No Known Activations