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

    Neuronpedia

    INDEX
    Explanations

    way of doing things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ینده
    0.39
     QtCore
    0.39
     ছুট
    0.37
     ಚಿ
    0.36
    ších
    0.36
    矣
    0.35
     얼마나
    0.35
    ნობ
    0.35
     මො
    0.35
    什么时候
    0.34
    POSITIVE LOGITS
     way
    3.77
     Way
    3.05
    Way
    2.98
     ways
    2.92
    way
    2.84
     WAY
    2.70
     cách
    2.63
     Ways
    2.45
    WAY
    2.44
    Ways
    2.38
    Act Density 0.183%

    No Known Activations