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

    Neuronpedia

    INDEX
    Explanations

    npm package management commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    핑크
    2.29
     както
    2.24
    nish
    2.21
    ി
    2.20
    ا
    2.17
    niger
    2.14
    ர
    2.13
    NSURL
    2.11
    ariance
    2.09
     sprung
    2.07
    POSITIVE LOGITS
    ০
    2.57
     anum
    2.48
    મ
    2.29
    र
    2.27
    bilical
    2.26
    ות
    2.22
    el
    2.22
     contradicting
    2.20
    isPrime
    2.20
     confusión
    2.16
    Act Density 0.028%

    No Known Activations