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

    Neuronpedia

    INDEX
    Explanations

    Reef, ball, Lord, company

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     //}
    0.48
     maliciously
    0.42
    얏
    0.42
    疫苗
    0.42
    存于互联网档案馆
    0.42
    )”.
    0.42
    विर
    0.41
     !}\
    0.40
     জলা
    0.39
     Smartphones
    0.39
    POSITIVE LOGITS
    grou
    0.42
    '
    0.41
     Company
    0.40
     affirmed
    0.40
    rå
    0.40
    ANZ
    0.38
    d
    0.38
    Company
    0.37
    to
    0.36
     long
    0.36
    Act Density 0.006%

    No Known Activations