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

    Neuronpedia

    INDEX
    Explanations

    AI platforms and models

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ཋ
    0.46
     wer
    0.44
     CLEAR
    0.44
    ಿಸ್
    0.43
     parum
    0.43
     suav
    0.43
     CUT
    0.42
     inhoud
    0.42
     ئۇ
    0.42
     coolest
    0.42
    POSITIVE LOGITS
    }
    0.48
    专辑
    0.42
    RouterModule
    0.41
    请求
    0.41
    ိတ်
    0.41
    shopify
    0.41
     Wrap
    0.40
    ‌
    0.40
     esempio
    0.40
    ra
    0.39
    Act Density 0.001%

    No Known Activations