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

    Neuronpedia

    INDEX
    Explanations

    Blazor exited score

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <unused253>
    0.25
    畬
    0.22
    🥬
    0.22
    ließlich
    0.22
    <unused480>
    0.22
    <unused982>
    0.21
    <unused1960>
    0.21
     سیاست
    0.21
    पैकी
    0.21
    <unused210>
    0.21
    POSITIVE LOGITS
     extravaganza
    0.21
    ра
    0.21
    se
    0.20
     (
    0.20
    ities
    0.20
    I
    0.20
    high
    0.20
    ка
    0.19
    ulence
    0.19
     project
    0.19
    Act Density 0.447%

    No Known Activations