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

    Neuronpedia

    INDEX
    Explanations

    several team, continually

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     engravings
    0.52
    जे
    0.51
     in
    0.51
     Divine
    0.51
     chuckled
    0.51
     drake
    0.51
     Lovely
    0.50
    主教
    0.50
     edible
    0.50
     পি
    0.49
    POSITIVE LOGITS
    asing
    0.53
    resar
    0.53
    imagem
    0.47
    arlings
    0.47
    ubert
    0.46
    ulton
    0.46
    θούν
    0.45
    uster
    0.45
    oad
    0.44
    ти
    0.43
    Act Density 0.000%

    No Known Activations