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

    Neuronpedia

    INDEX
    Explanations

    program is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cómoda
    0.41
     இதன்
    0.40
     Sí
    0.40
     الجمهور
    0.38
     astronaut
    0.38
     جوہری
    0.38
    囵
    0.38
     spazio
    0.37
     llegue
    0.37
    ♯
    0.37
    POSITIVE LOGITS
    etown
    0.39
    izers
    0.38
    Nz
    0.38
    LAM
    0.38
    gel
    0.37
    thia
    0.37
    vot
    0.37
    abbas
    0.36
    kotlin
    0.36
    typescript
    0.36
    Act Density 0.001%

    No Known Activations