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

    Neuronpedia

    INDEX
    Explanations

    code error checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;//
    0.44
    ,“
    0.37
    azada
    0.37
    κια
    0.37
    handle
    0.36
    ik
    0.36
    ,’
    0.36
    紧急
    0.36
    pan
    0.35
    uncia
    0.35
    POSITIVE LOGITS
     সম্পাদকীয়
    0.40
    తిరే
    0.38
    翕
    0.38
     Peaceful
    0.38
     guérison
    0.37
    ).\\
    0.37
    などで
    0.37
    ى
    0.37
     Sant
    0.36
     Aztecs
    0.36
    Act Density 0.012%

    No Known Activations