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

    Neuronpedia

    INDEX
    Explanations

    both of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tinham
    0.85
     willst
    0.75
     hacen
    0.75
     pâte
    0.70
     प्रीम
    0.69
     پیسې
    0.69
    都是
    0.69
     hatten
    0.69
     wollten
    0.68
     tengo
    0.67
    POSITIVE LOGITS
     Pl
    0.65
     oluşan
    0.57
     of
    0.56
     Z
    0.53
    インテリア
    0.52
     Il
    0.52
     itibaren
    0.51
     internal
    0.51
     index
    0.51
     Из
    0.50
    Act Density 0.005%

    No Known Activations