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

    Neuronpedia

    INDEX
    Explanations

    what I can provide

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     *
    0.38
     the
    0.38
    -
    0.38
     some
    0.38
     two
    0.37
     pines
    0.37
     shoes
    0.37
     you
    0.37
     o
    0.36
     anyway
    0.36
    POSITIVE LOGITS
    provide
    0.45
    Provide
    0.43
     забезпе
    0.42
     نہایت
    0.42
     همچنین
    0.41
     اہم
    0.41
    明確
    0.40
     provide
    0.40
     تعمل
    0.40
     प्रदान
    0.39
    Act Density 0.027%

    No Known Activations