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

    Neuronpedia

    INDEX
    Explanations

    composition tablesreduce markersown hairstylish design

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ರಲ್ಲಿ
    0.52
     musul
    0.49
    wheres
    0.47
    how
    0.46
    শিপ
    0.45
    where
    0.44
    ជាមួយនឹង
    0.44
     Bagaimana
    0.43
    वेळी
    0.43
     Where
    0.43
    POSITIVE LOGITS
    Drag
    0.45
    írás
    0.44
    IM
    0.42
    P
    0.42
    ù
    0.41
    Í
    0.41
    OS
    0.39
    AB
    0.39
    í
    0.38
    ök
    0.38
    Act Density 0.001%

    No Known Activations