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

    Neuronpedia

    INDEX
    Explanations

    start and end

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ईद
    0.32
    ଚ
    0.32
    owy
    0.31
    ivă
    0.31
    ühlt
    0.31
    жом
    0.31
    াস
    0.30
    ებული
    0.30
     thập
    0.30
    ónicas
    0.30
    POSITIVE LOGITS
     other
    0.49
     অন্যান্য
    0.39
    /
    0.36
     combination
    0.35
     ఇతర
    0.33
    other
    0.33
    or
    0.33
     autres
    0.32
     respective
    0.32
     P
    0.32
    Act Density 0.094%

    No Known Activations