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

    Neuronpedia

    INDEX
    Explanations

    technical how-to questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     కే
    0.48
    之後
    0.45
    ם
    0.45
     ডিভাইস
    0.44
    argon
    0.44
    derr
    0.44
    bd
    0.44
    েরা
    0.44
    ọn
    0.43
    חנו
    0.43
    POSITIVE LOGITS
     cap
    0.54
    ，
    0.49
     nears
    0.47
     earners
    0.46
     Cen
    0.45
     woodland
    0.45
     battles
    0.44
     shady
    0.44
     generals
    0.44
     tròn
    0.43
    Act Density 0.002%

    No Known Activations