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

    Neuronpedia

    INDEX
    Explanations

    any + noun

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     used
    0.15
     pulled
    0.15
     made
    0.14
     optimized
    0.14
     using
    0.14
     generated
    0.14
     facilitated
    0.14
     an
    0.13
     either
    0.13
    matic
    0.13
    POSITIVE LOGITS
     διαφορε
    0.17
     sayıda
    0.17
     dintre
    0.16
     verschiedene
    0.16
     kinds
    0.16
     different
    0.16
    不同的
    0.16
    異なる
    0.16
     разных
    0.16
     forskjellige
    0.15
    Act Density 0.183%

    No Known Activations