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

    Neuronpedia

    INDEX
    Explanations

    code snippets and documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ിക്കുകയും
    0.43
    blah
    0.41
     এইরূপ
    0.41
     Донец
    0.38
     Scandinavia
    0.38
    这句话
    0.37
    这种情况
    0.37
     Rasmussen
    0.37
    濱
    0.37
    Lack
    0.36
    POSITIVE LOGITS
    `:
    0.48
    рует
    0.46
    ):
    0.44
    ():
    0.42
     hauptsächlich
    0.41
     ():
    0.41
     mainly
    0.40
    <code>
    0.39
     kilku
    0.39
    **:
    0.39
    Act Density 0.008%

    No Known Activations