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

    Neuronpedia

    INDEX
    Explanations

    comparison or degree

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     unincorporated
    0.49
     sinners
    0.45
     dava
    0.42
     shingles
    0.42
     attivo
    0.40
     absentee
    0.37
     ironically
    0.37
     hinting
    0.37
     currant
    0.37
     truce
    0.37
    POSITIVE LOGITS
    волю
    0.49
    })
    0.46
    乐趣
    0.44
     હંમે
    0.44
    ारक
    0.42
    klady
    0.42
    atele
    0.41
     ২০১১
    0.41
     प्रीवियस
    0.41
    🎓
    0.40
    Act Density 0.023%

    No Known Activations