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

    Neuronpedia

    INDEX
    Explanations

    ARIMA models and Trello

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    I
    0.91
    v
    0.83
    sh
    0.78
    the
    0.76
    ib
    0.76
    .
    0.74
    ir
    0.73
    rit
    0.73
    ő
    0.73
    ali
    0.72
    POSITIVE LOGITS
     was
    1.07
     were
    0.98
     has
    0.88
     to
    0.84
     heeft
    0.82
     had
    0.82
    ות
    0.82
     is
    0.78
     hadden
    0.77
    (
    0.75
    Act Density 0.005%

    No Known Activations