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

    Neuronpedia

    INDEX
    Explanations

    have a

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ayant
    0.28
     utilizzando
    0.27
    あらゆる
    0.27
     mesmos
    0.27
    라면
    0.26
     selben
    0.26
     Not
    0.26
    同一个
    0.25
     offrant
    0.25
     Aynı
    0.25
    POSITIVE LOGITS
     been
    0.89
    been
    0.70
    Been
    0.63
     BEEN
    0.59
     undergone
    0.58
     Been
    0.54
     bisogno
    0.53
     sido
    0.50
     fått
    0.50
     ollut
    0.49
    Act Density 0.155%

    No Known Activations