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

    Neuronpedia

    INDEX
    Explanations

    specific time massive critical

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    imi
    0.52
    ara
    0.51
    ain
    0.50
     regulación
    0.49
    アン
    0.49
    含ま
    0.48
     precarious
    0.46
    ale
    0.45
    aran
    0.45
    ne
    0.45
    POSITIVE LOGITS
    种
    0.53
    现在
    0.48
    бою
    0.48
    лью
    0.48
     Sandler
    0.48
     Elovl
    0.46
    闪
    0.46
    㩴
    0.46
    صر
    0.45
     অধর
    0.45
    Act Density 0.000%

    No Known Activations