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

    Neuronpedia

    INDEX
    Explanations

    ' phrases usually followed by t

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ukup
    0.50
    rschein
    0.49
    มุม
    0.49
    awy
    0.48
     수익
    0.48
    ू
    0.48
    ก
    0.47
     اک
    0.47
     आरंभ
    0.47
     안내
    0.47
    POSITIVE LOGITS
     aprobación
    0.50
    টাল
    0.49
     cier
    0.49
    स्पिर
    0.48
    V
    0.48
     gives
    0.48
    णिमा
    0.48
     vál
    0.48
    もら
    0.47
     cuyas
    0.47
    Act Density 0.000%

    No Known Activations