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

    Neuronpedia

    INDEX
    Explanations

    disrupts, survive, clinic, finally

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     statunitense
    0.40
     anthropology
    0.40
    の変化
    0.37
    生物
    0.37
    内心
    0.37
     ಕ್ಷೇತ್ರದಲ್ಲಿ
    0.37
     biologiques
    0.37
    jdField
    0.37
    >→</
    0.37
     ഭൂ
    0.36
    POSITIVE LOGITS
     Hut
    0.44
     TÜ
    0.44
     sev
    0.43
     Cyr
    0.40
     T
    0.40
     py
    0.39
     Т
    0.38
    UT
    0.38
     air
    0.38
    Wing
    0.38
    Act Density 0.001%

    No Known Activations