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

    Neuronpedia

    INDEX
    Explanations

    no warranty or automated

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    warranty
    0.42
     warranty
    0.40
     त्यात
    0.38
    шев
    0.38
    laughs
    0.37
     Medicaid
    0.37
     Warranty
    0.37
    一年
    0.36
    अधिकांश
    0.36
    椂
    0.36
    POSITIVE LOGITS
     của
    0.41
    Toys
    0.37
     of
    0.37
     zh
    0.36
     সহযোগ
    0.36
    LOUISE
    0.36
    hanam
    0.35
    Kay
    0.35
    FTP
    0.35
     pound
    0.34
    Act Density 0.000%

    No Known Activations