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

    Neuronpedia

    INDEX
    Explanations

    sit / sitting / sat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     hanging
    0.34
     incriminating
    0.33
    谗
    0.32
     alarg
    0.32
    ർഡ്
    0.31
    MILLISE
    0.31
     /=
    0.31
     SNA
    0.31
    sda
    0.31
     září
    0.30
    POSITIVE LOGITS
     sit
    0.77
    坐
    0.74
     앉
    0.74
     Sit
    0.69
    Sit
    0.69
     duduk
    0.66
     sits
    0.66
     sitting
    0.63
    sit
    0.63
     ngồi
    0.63
    Act Density 0.011%

    No Known Activations