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

    Neuronpedia

    INDEX
    Explanations

    density and estimation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ꞎ
    0.44
    aży
    0.43
     प्रजनन
    0.42
     quedado
    0.42
     frequência
    0.42
    cześ
    0.41
     wcześniej
    0.40
     llevo
    0.40
     invál
    0.40
    ៕
    0.40
    POSITIVE LOGITS
    ек
    0.47
    の
    0.47
    ד
    0.47
     and
    0.46
    의
    0.46
     во
    0.45
    ﾕ
    0.44
     COLOR
    0.44
    <0xEF>
    0.43
    ث
    0.42
    Act Density 0.001%

    No Known Activations