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

    Neuronpedia

    INDEX
    Explanations

    add er to words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     கொண்டு
    0.84
     succession
    0.81
    াপন্ন
    0.80
    বার
    0.78
    鍔
    0.78
     निखिल
    0.78
     νη
    0.77
    ware
    0.76
     пут
    0.76
    echen
    0.75
    POSITIVE LOGITS
     hinzu
    1.24
    /−
    1.19
    _+
    1.12
     (+)
    1.11
     Ababa
    1.11
    itionally
    1.07
    subdirectory
    1.06
    ictive
    1.05
    itions
    1.05
    ">+</
    1.03
    Act Density 0.300%

    No Known Activations