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

    Neuronpedia

    INDEX
    Explanations

    me to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     עבור
    0.83
     হওয়া
    0.78
    ക്കിയി
    0.77
    രുടെയും
    0.76
    ሉት
    0.76
    ড়ানো
    0.72
    వడం
    0.72
     পারেন
    0.71
    नाले
    0.70
     பதிலாக
    0.68
    POSITIVE LOGITS
     to
    5.66
    to
    4.20
     To
    3.29
    To
    3.16
     να
    2.69
     TO
    2.59
     إلى
    2.57
     để
    2.44
     upang
    2.17
     toa
    2.17
    Act Density 6.233%

    No Known Activations