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

    Neuronpedia

    INDEX
    Explanations

    queries and issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    晧
    0.38
    πλ
    0.37
    填写
    0.37
     Linde
    0.36
     progress
    0.36
     COVID
    0.36
    プリン
    0.36
     lectura
    0.35
     лига
    0.35
    ಚ್ಚ
    0.35
    POSITIVE LOGITS
     eignet
    0.43
    )=$
    0.43
    ர்ப
    0.40
    MLE
    0.39
    ರಿಸ
    0.38
    $=\
    0.37
     datth
    0.37
     carn
    0.36
    )=(\
    0.36
    =$\
    0.36
    Act Density 0.000%

    No Known Activations