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

    Neuronpedia

    INDEX
    Explanations

    executive summary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0xA6>
    0.99
    ки
    0.98
    жнарод
    0.93
    ۳
    0.89
    ای
    0.86
    ३
    0.85
    よい
    0.84
     soprattutto
    0.84
    ுள்ளது
    0.83
    Imagem
    0.82
    POSITIVE LOGITS
    es
    0.89
    lim
    0.88
     deri
    0.86
    nads
    0.85
    fact
    0.84
     vesicles
    0.84
     raíces
    0.83
     individuos
    0.83
    lings
    0.82
    cluding
    0.82
    Act Density 0.002%

    No Known Activations