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

    Neuronpedia

    INDEX
    Explanations

    for

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    way
    -0.07
    .Cast
    -0.06
     flushed
    -0.06
     restoration
    -0.06
     ensures
    -0.06
     gesture
    -0.06
     midway
    -0.06
     transforms
    -0.06
     remake
    -0.06
     unseen
    -0.06
    POSITIVE LOGITS
    /$',
    0.07
    hound
    0.06
    Uploader
    0.06
    library
    0.06
    uchar
    0.06
     ciz
    0.06
     rost
    0.06
    lif
    0.06
    enin
    0.06
     Located
    0.06
    Act Density 0.007%

    No Known Activations