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

    Neuronpedia

    INDEX
    Explanations

    person's name followed by relation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kilogram
    0.43
    крыть
    0.43
    OutgoingRiver
    0.43
     girly
    0.43
    这种
    0.41
    sq
    0.41
     יכול
    0.40
    这两个
    0.40
    tpVar
    0.40
     मिल्क
    0.39
    POSITIVE LOGITS
     (
    0.37
    spouse
    0.35
     Ehe
    0.34
    ਾਲ
    0.34
     wife
    0.34
     spouse
    0.34
     esposa
    0.34
    hausen
    0.32
    ன்
    0.32
     ibid
    0.32
    Act Density 0.008%

    No Known Activations