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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     चाहे
    -0.09
     संकट
    -0.09
     Somehow
    -0.09
     উৎ
    -0.09
     সাক্ষ
    -0.09
     suç
    -0.09
     संत
    -0.09
     घ
    -0.08
    صاف
    -0.08
     उत्कृष्ट
    -0.08
    POSITIVE LOGITS
     depending
    0.09
     dependendo
    0.09
    depending
    0.09
     verfügbar
    0.09
     확인
    0.09
     deprecated
    0.09
     restrictions
    0.09
     limitations
    0.09
    Unsupported
    0.09
     grub
    0.09
    Act Density 0.036%

    No Known Activations