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

    Neuronpedia

    INDEX
    Explanations

    scale=

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ವಾಸ
    0.48
    습니다
    0.44
    ם
    0.43
    였다
    0.43
    ர
    0.42
    ום
    0.41
    ហារ
    0.39
     shades
    0.39
    нора
    0.39
    門
    0.38
    POSITIVE LOGITS
     escala
    0.62
     scale
    0.54
     Scale
    0.53
    scale
    0.51
     escalas
    0.50
    Scale
    0.49
     Scales
    0.49
     SCALE
    0.48
    RATE
    0.46
     scales
    0.45
    Act Density 0.000%

    No Known Activations