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

    Neuronpedia

    INDEX
    Explanations

    code documentation keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    च
    0.48
    व्यव
    0.43
    वारी
    0.42
    USA
    0.41
    Revenue
    0.41
    W
    0.41
     Ist
    0.41
    нили
    0.41
    되면
    0.41
    ENERGY
    0.41
    POSITIVE LOGITS
     conjure
    0.42
     शहनाज
    0.42
     detrás
    0.40
     paisajes
    0.40
     फतेह
    0.38
     clearContext
    0.38
    ெற்ற
    0.38
     github
    0.38
     creado
    0.38
     shootings
    0.37
    Act Density 0.001%

    No Known Activations