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

    Neuronpedia

    INDEX
    Explanations

    screen height and margin

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     vouchers
    0.40
     overlooked
    0.38
     voucher
    0.38
     emojis
    0.38
     disregarded
    0.38
     applauded
    0.38
     dikeluarkan
    0.38
     affiliates
    0.37
     apoyar
    0.37
     obviamente
    0.36
    POSITIVE LOGITS
     अधिकतम
    0.51
    max
    0.43
    margin
    0.42
     長
    0.42
    maxLength
    0.42
     நீ
    0.41
     максима
    0.41
    height
    0.41
     길이
    0.41
    å
    0.41
    Act Density 0.028%

    No Known Activations