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

    Neuronpedia

    INDEX
    Explanations

    code and unicode characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     userdata
    0.39
    素晴
    0.39
     conserva
    0.39
    дів
    0.37
     तलैया
    0.37
     Marissa
    0.37
    াইয়
    0.37
    䒱
    0.36
     தள
    0.35
     suma
    0.35
    POSITIVE LOGITS
    貝
    0.37
    ヒ
    0.37
     WIND
    0.37
    මය
    0.36
    ilty
    0.35
     இருப்பது
    0.35
     फ्रे
    0.34
    坳
    0.34
    Hispanic
    0.33
    trace
    0.33
    Act Density 0.002%

    No Known Activations