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

    Neuronpedia

    INDEX
    Explanations

    life followed by nouns

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wizards
    0.92
    োগ
    0.88
    ሁ
    0.86
    tion
    0.84
    kHz
    0.82
    ierten
    0.82
    ्रिया
    0.81
    प्लो
    0.77
    rophy
    0.76
    aler
    0.74
    POSITIVE LOGITS
     expectancy
    1.94
    blood
    1.51
    स्टाइल
    1.29
    शैली
    1.28
     span
    1.22
     lived
    1.21
    boats
    1.16
     force
    1.15
    साथ
    1.12
    forms
    1.11
    Act Density 0.089%

    No Known Activations