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

    Neuronpedia

    INDEX
    Explanations

    movie trailer script

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.80
     synagogue
    0.66
    るので
    0.66
     legume
    0.64
    สัมพันธ์
    0.64
    \
    0.63
     magistrate
    0.61
    อยู่
    0.60
     pineapple
    0.59
    OR
    0.59
    POSITIVE LOGITS
     trailers
    1.29
     Trailers
    1.06
     Trailer
    0.98
    Trailer
    0.92
     trailer
    0.89
     equivoc
    0.86
    ő
    0.77
    trailer
    0.75
     avances
    0.73
    𝖊
    0.73
    Act Density 0.002%

    No Known Activations