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

    Neuronpedia

    INDEX
    Explanations

    go back to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ul
    0.52
     sabbam
    0.46
     oblast
    0.46
     cioc
    0.46
    ленная
    0.44
     Makassar
    0.44
    ढ़
    0.44
    𝚕
    0.44
    ණය
    0.44
     kön
    0.44
    POSITIVE LOGITS
    意的
    0.51
     Wasn
    0.49
    克的
    0.47
     Cited
    0.45
     Trump
    0.45
     Directly
    0.44
    本身的
    0.44
    ುಂಬ
    0.43
    hoti
    0.43
    大了
    0.43
    Act Density 0.025%

    No Known Activations