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

    Neuronpedia

    INDEX
    Explanations

    other concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     و
    0.44
     và
    0.41
     albo
    0.40
     terrific
    0.38
     oraz
    0.38
     dhe
    0.37
     és
    0.36
     supaya
    0.36
    و
    0.35
    とその
    0.34
    POSITIVE LOGITS
     ఇతర
    0.51
     અન્ય
    0.46
     других
    0.43
    अन्य
    0.43
    其他
    0.41
     інших
    0.41
     অন্যান্য
    0.40
     다른
    0.40
     diğer
    0.40
     інші
    0.39
    Act Density 0.605%

    No Known Activations