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

    Neuronpedia

    INDEX
    Explanations

    have access or have them

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     our
    0.46
     PAST
    0.43
     cannot
    0.43
     unsere
    0.43
     BASE
    0.42
     Viva
    0.42
     SPIR
    0.42
     Viv
    0.41
     Shooting
    0.40
     many
    0.39
    POSITIVE LOGITS
     melakukannya
    0.89
     hacerlo
    0.73
     farlo
    0.65
     ĝi
    0.59
     તેને
    0.56
    それを
    0.55
     ایسا
    0.54
     ذلك
    0.53
    这样做
    0.53
     ervan
    0.51
    Act Density 0.174%

    No Known Activations