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

    Neuronpedia

    INDEX
    Explanations

    subtly or

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     आइडेंट
    0.44
    ް
    0.43
    StringEncoding
    0.42
     receivables
    0.41
     assistant
    0.41
     Comun
    0.41
     ರೋ
    0.41
    बीआई
    0.40
    াকিস্ত
    0.40
     Asst
    0.40
    POSITIVE LOGITS
    ETE
    0.43
    ERA
    0.40
    EDE
    0.40
    онов
    0.38
    डाउन
    0.37
    ULES
    0.37
    orschungs
    0.36
    IVERY
    0.35
    نز
    0.35
    بوب
    0.35
    Act Density 0.001%

    No Known Activations