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

    Neuronpedia

    INDEX
    Explanations

    HTML websites

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಪಡ
    0.48
    ব
    0.46
    ghis
    0.46
     find
    0.45
     formado
    0.45
     angew
    0.44
     post
    0.44
    ב
    0.44
     give
    0.44
     mitigate
    0.43
    POSITIVE LOGITS
    erent
    0.55
     cartridges
    0.48
    ਿਆਂ
    0.48
     дохода
    0.45
     निर्मित
    0.44
    祅
    0.44
    เหล่า
    0.44
    忤
    0.43
    Һ
    0.43
    لہ
    0.43
    Act Density 0.001%

    No Known Activations