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

    Neuronpedia

    INDEX
    Explanations

    list items with specific indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    公众
    0.40
    バランス
    0.40
    师傅
    0.39
     благодар
    0.38
    Limited
    0.38
     "@{
    0.36
    addHandler
    0.36
    handle
    0.36
     ограничен
    0.36
     উৎপ
    0.35
    POSITIVE LOGITS
     absc
    0.41
     gals
    0.41
     humanities
    0.40
    نین
    0.39
     trees
    0.38
     kabhi
    0.38
    ']*
    0.38
    രണ
    0.38
     didn
    0.38
     쭉
    0.37
    Act Density 0.001%

    No Known Activations