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

    Neuronpedia

    INDEX
    Explanations

    therefore or accordingly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     certain
    0.40
    жима
    0.39
     जैसा
    0.37
    چا
    0.36
    coid
    0.36
     cystic
    0.36
    Dl
    0.36
     cycling
    0.34
     circ
    0.33
    agge
    0.33
    POSITIVE LOGITS
    对此
    1.18
     accordingly
    1.07
    为此
    1.04
     dafür
    0.96
     이에
    0.91
     hierv
    0.89
     nisso
    0.83
     لهذا
    0.82
     Accordingly
    0.82
     بهذا
    0.80
    Act Density 0.020%

    No Known Activations