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

    Neuronpedia

    INDEX
    Explanations

    numbers with decimal points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     gás
    0.80
     night
    0.76
     వె
    0.75
     ساخت
    0.74
    粿
    0.74
     Nacht
    0.74
    Yi
    0.72
     Barros
    0.72
    易
    0.71
     nacht
    0.71
    POSITIVE LOGITS
    open
    0.75
    own
    0.71
    oop
    0.69
    োলার
    0.67
    odata
    0.67
    oit
    0.65
    <0x80>
    0.64
    object
    0.64
    用の
    0.64
    olites
    0.63
    Act Density 0.215%

    No Known Activations