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

    Neuronpedia

    INDEX
    Explanations

    Do Androids Dream of Electric Sheep?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Caedwalla
    0.58
     années
    0.56
    なかった
    0.55
    வியில்
    0.55
    💓
    0.54
    邡
    0.54
    었다
    0.51
    embrie
    0.51
     エネルギー
    0.51
     multitudes
    0.51
    POSITIVE LOGITS
    z
    0.67
    u
    0.63
    1
    0.62
    f
    0.61
    y
    0.58
    R
    0.58
    ib
    0.57
    c
    0.57
    ido
    0.56
    in
    0.55
    Act Density 0.000%

    No Known Activations