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

    Neuronpedia

    INDEX
    Explanations

    sound and bound endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Ridley
    0.81
    ologien
    0.74
    浠
    0.73
    CALLBACK
    0.72
    ວິ
    0.72
    Adrian
    0.71
     γίνεται
    0.71
    serif
    0.71
     cidad
    0.71
    鏁
    0.71
    POSITIVE LOGITS
    nd
    1.82
     nd
    1.80
    und
    1.77
    UND
    1.74
    ND
    1.71
     ND
    1.69
    ond
    1.69
    unda
    1.69
    ound
    1.63
    нд
    1.62
    Act Density 0.193%

    No Known Activations