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

    Neuronpedia

    INDEX
    Explanations

    social care and functional concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ل
    0.70
    د
    0.63
    ر
    0.54
    ب
    0.54
    ف
    0.54
    頔
    0.54
     unten
    0.52
     busier
    0.50
    ды
    0.50
    做
    0.50
    POSITIVE LOGITS
    ра
    0.59
    STRING
    0.52
     Кор
    0.50
     biocompat
    0.49
    м
    0.49
    STAT
    0.48
     जुड़े
    0.48
     Ко
    0.47
     orientale
    0.46
     Ratch
    0.46
    Act Density 0.001%

    No Known Activations