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

    Neuronpedia

    INDEX
    Explanations

    Pearson rating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     сумма
    0.81
     під
    0.80
     گل
    0.77
     Ра
    0.76
     diperoleh
    0.75
     =>{
    0.74
     Ejemplo
    0.74
    CaO
    0.74
    centro
    0.74
     الإ
    0.74
    POSITIVE LOGITS
     sober
    0.62
    rera
    0.53
     nonnegative
    0.52
     reinstated
    0.51
     despised
    0.51
     reinstate
    0.49
    tsy
    0.48
     blindness
    0.48
     जनगणना
    0.48
    ખ્યા
    0.47
    Act Density 0.001%

    No Known Activations