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

    Neuronpedia

    INDEX
    Explanations

    however, offering alternatives

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Política
    0.46
     बड़ी
    0.44
     परेशानी
    0.44
     बड़ी
    0.44
    "}
    0.44
    “
    0.42
    Protection
    0.41
    Jw
    0.41
     CuSO
    0.41
    JPEG
    0.40
    POSITIVE LOGITS
     as
    0.46
    چ
    0.45
    :
    0.42
    τα
    0.41
    ის
    0.40
    ม
    0.40
    ј
    0.40
    k
    0.38
    מ
    0.38
     WERE
    0.38
    Act Density 0.744%

    No Known Activations