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

    Neuronpedia

    INDEX
    Explanations

    identity or status

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     spesso
    0.47
    σία
    0.43
     talento
    0.43
     difficol
    0.41
     viene
    0.40
    が無い
    0.39
     lucru
    0.39
    ع
    0.39
     della
    0.38
     suele
    0.38
    POSITIVE LOGITS
    看待
    0.52
     পরিণত
    0.50
     घोषित
    0.50
     Identity
    0.49
    身份
    0.49
     haline
    0.48
     proclaimed
    0.48
    称号
    0.47
     बनना
    0.46
    로서
    0.46
    Act Density 0.213%

    No Known Activations