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

    Neuronpedia

    INDEX
    Explanations

    me here

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ற்கான
    0.40
     Раз
    0.39
     முன்ன
    0.38
     sosten
    0.38
    ⛈
    0.38
     cropped
    0.37
    нах
    0.37
    ্া
    0.36
    দ্ম
    0.36
    શ્ર
    0.36
    POSITIVE LOGITS
     rules
    0.35
     Worldwide
    0.35
     FT
    0.35
    icie
    0.33
    William
    0.33
     opinions
    0.33
     Continental
    0.32
     قاب
    0.32
    Worldwide
    0.32
     Kern
    0.32
    Act Density 0.011%

    No Known Activations