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

    Neuronpedia

    INDEX
    Explanations

    explanation of lists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused2199>
    0.30
    τσι
    0.29
    이
    0.28
    ља
    0.28
    си
    0.27
    κτήθηκε
    0.27
    ст
    0.27
    <unused2125>
    0.27
    罍
    0.27
    гина
    0.26
    POSITIVE LOGITS
     (
    0.28
    layer
    0.27
     =
    0.26
     باستخدام
    0.25
    aturally
    0.25
     +
    0.24
    ibration
    0.24
     Boolean
    0.24
     Yes
    0.23
    ryption
    0.23
    Act Density 0.563%

    No Known Activations