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

    Neuronpedia

    INDEX
    Explanations

    replace ... with

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    باس
    0.45
     বৈদেশিক
    0.43
    犟
    0.42
    ेश्च
    0.42
    夆
    0.41
     बैटरी
    0.40
     لوبوي
    0.40
    ableConcept
    0.40
     европей
    0.40
    albeit
    0.40
    POSITIVE LOGITS
     common
    0.47
     lay
    0.46
     sites
    0.45
    oleh
    0.45
     arrogant
    0.44
    ара
    0.44
     intent
    0.43
     community
    0.43
    2
    0.43
     places
    0.41
    Act Density 0.001%

    No Known Activations