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

    Neuronpedia

    INDEX
    Explanations

    corner locations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    薙
    0.44
    ClCompile
    0.38
     sust
    0.37
    ത്തില്‍
    0.35
    ાઓ
    0.34
     bruit
    0.34
    导
    0.34
     Wechsler
    0.34
     синх
    0.34
    धारण
    0.33
    POSITIVE LOGITS
     corner
    4.72
    Corner
    4.28
     corners
    4.25
    corner
    4.25
     Corner
    4.22
    corners
    3.73
     Corners
    3.72
    Corners
    3.55
    コーナー
    3.17
     esquina
    3.14
    Act Density 0.043%

    No Known Activations