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

    Neuronpedia

    INDEX
    Explanations

    code blocks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    див
    0.44
    собенности
    0.38
     JavaScript
    0.38
    したり
    0.38
     ISSN
    0.36
    τσ
    0.36
    темати
    0.35
    ையில்
    0.35
     JAVA
    0.35
     Prop
    0.34
    POSITIVE LOGITS
     भैर
    0.39
     혹
    0.38
    íncipe
    0.38
     আমিও
    0.38
     palestra
    0.38
     مرحوم
    0.38
     #
    0.36
     இது
    0.36
    utico
    0.36
     ഇത
    0.36
    Act Density 0.014%

    No Known Activations