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

    Neuronpedia

    INDEX
    Explanations

    obfuscation techniques

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ihe
    1.85
     dampers
    1.83
    EM
    1.73
     noen
    1.65
    씩
    1.58
     pamoja
    1.57
     griev
    1.55
    ﻴ
    1.54
    ED
    1.46
     moor
    1.45
    POSITIVE LOGITS
    ك
    2.00
     وعلى
    1.93
    اء
    1.72
    Cré
    1.72
    های
    1.71
    دي
    1.70
    féle
    1.64
    است
    1.63
    ுக்கு
    1.60
    ین
    1.59
    Act Density 0.000%

    No Known Activations