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

    Neuronpedia

    INDEX
    Explanations

    math properties and algebra

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    τά
    0.45
     Compiler
    0.40
     Twins
    0.39
     dòng
    0.39
    تون
    0.38
    ⌚
    0.37
    盞
    0.36
     замы
    0.36
    apture
    0.35
    ဆိုင်
    0.35
    POSITIVE LOGITS
     Prussia
    0.39
    هن
    0.38
     Pythagoras
    0.38
     alerg
    0.38
     rings
    0.38
     fog
    0.38
    磪
    0.38
     문제를
    0.37
    jung
    0.37
     Ring
    0.37
    Act Density 0.003%

    No Known Activations