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

    Neuronpedia

    INDEX
    Explanations

    without

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ímav
    0.70
    જુ
    0.61
    䔀
    0.60
    bigvee
    0.58
     lắm
    0.57
     воспомина
    0.57
    خر
    0.56
    ũng
    0.56
    或者是
    0.56
    ान
    0.55
    POSITIVE LOGITS
     without
    5.76
    without
    5.25
     Without
    5.20
     tanpa
    5.09
    Without
    5.03
     без
    4.95
     WITHOUT
    4.80
     ohne
    4.76
     zonder
    4.71
     senza
    4.51
    Act Density 1.471%

    No Known Activations