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

    Neuronpedia

    INDEX
    Explanations

    from X to Y

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     receipts
    0.68
    TabText
    0.67
    Urls
    0.67
     шрифт
    0.66
     extras
    0.65
    emiah
    0.65
    eis
    0.64
    지도
    0.63
    ദേ
    0.62
    โย
    0.62
    POSITIVE LOGITS
     increasing
    2.72
    Increasing
    2.54
    increasing
    2.52
     Increasing
    2.47
     decreasing
    2.28
    decreasing
    2.08
     increasingly
    2.00
     progressively
    1.99
     escalating
    1.77
     creciente
    1.71
    Act Density 0.302%

    No Known Activations