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

    Neuronpedia

    INDEX
    Explanations

    Forbes .com links

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    shows
    0.66
     shows
    0.64
     phục
    0.63
     beobachten
    0.61
     выступления
    0.60
     प्रकट
    0.59
    Ins
    0.59
     Ona
    0.58
     show
    0.58
     ere
    0.58
    POSITIVE LOGITS
    octrl
    0.59
     Cascade
    0.56
    }']
    0.56
     Católica
    0.55
     Jesuits
    0.54
     Javier
    0.54
     López
    0.54
     Alberto
    0.53
    édération
    0.53
    是你
    0.53
    Act Density 0.003%

    No Known Activations