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

    Neuronpedia

    INDEX
    Explanations

    Here's explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     била
    0.76
    olischen
    0.75
     কৰি
    0.75
     ਬਾ
    0.72
    ющими
    0.72
     FIXME
    0.71
     করেনি
    0.70
    륭
    0.69
     innymi
    0.69
     mogao
    0.68
    POSITIVE LOGITS
    fordshire
    1.39
    inafter
    1.27
     we
    1.13
     lies
    1.07
     goes
    1.02
     Comes
    1.01
    below
    0.96
    fords
    0.95
     comes
    0.93
    after
    0.92
    Act Density 0.203%

    No Known Activations