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

    Neuronpedia

    INDEX
    Explanations

    offensive sunflower now

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ASN
    0.52
    NULL
    0.52
    as
    0.51
     as
    0.50
    ointers
    0.49
    ET
    0.49
    ouvement
    0.49
    oer
    0.48
    ast
    0.48
     然後
    0.48
    POSITIVE LOGITS
     mish
    0.50
     negligently
    0.49
    И
    0.48
    가를
    0.47
    క్కు
    0.47
    가가
    0.47
    ной
    0.47
     crumpled
    0.47
     care
    0.47
    мах
    0.47
    Act Density 0.000%

    No Known Activations