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

    Neuronpedia

    INDEX
    Explanations

    who would win

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     прогре
    0.44
     พ
    0.44
     навча
    0.43
     geheel
    0.41
    尟
    0.41
     ਜ
    0.40
     trách
    0.40
    тро
    0.40
     озера
    0.40
    แต่
    0.40
    POSITIVE LOGITS
     overfitting
    0.51
     epigenetic
    0.49
     ephemeral
    0.48
     orderBy
    0.47
     pathogen
    0.45
     pathogens
    0.45
     pathogenic
    0.45
     fabrics
    0.45
     genomics
    0.45
     cleric
    0.44
    Act Density 0.002%

    No Known Activations