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

    Neuronpedia

    INDEX
    Explanations

    Gemma, Netherlands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kõik
    0.66
     самый
    0.59
    すべての
    0.57
     această
    0.55
     найбільш
    0.55
    ătur
    0.52
     kõige
    0.52
     scrollBody
    0.51
     пър
    0.51
    लेला
    0.50
    POSITIVE LOGITS
     United
    0.60
    United
    0.55
    +
    0.54
     Himalayas
    0.50
    US
    0.50
    USA
    0.50
     Vereinigten
    0.50
     Nunca
    0.49
    MeToo
    0.49
    NYSE
    0.48
    Act Density 0.018%

    No Known Activations