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

    Neuronpedia

    INDEX
    Explanations

    lottery-style random draws

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     umum
    0.45
     আসামি
    0.43
    アシ
    0.42
    ild
    0.42
     هزار
    0.40
    adas
    0.40
     помощь
    0.39
    iddel
    0.39
     kac
    0.38
     интернете
    0.38
    POSITIVE LOGITS
    ين
    0.53
     whereby
    0.51
     ovaj
    0.48
    扃
    0.48
    _*
    0.47
    این
    0.46
     这个
    0.45
     scrot
    0.45
     یہ
    0.44
    یث
    0.44
    Act Density 0.008%

    No Known Activations