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

    Neuronpedia

    INDEX
    Explanations

    stand up, stand against, stand out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.38
    мот
    0.37
     surfacing
    0.36
    écut
    0.34
    laying
    0.34
    verse
    0.34
     liegt
    0.33
    lice
    0.33
    lc
    0.33
    kład
    0.32
    POSITIVE LOGITS
     stood
    1.04
     debout
    1.02
     berdiri
    0.98
     Stand
    0.97
    Stand
    0.95
     stand
    0.92
     Stands
    0.92
     Standing
    0.92
     STAND
    0.92
     standing
    0.88
    Act Density 0.011%

    No Known Activations