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

    Neuronpedia

    INDEX
    Explanations

    origin began started

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    herence
    0.66
     توانائی
    0.65
    চার
    0.64
     constitute
    0.64
     умова
    0.64
     ብቻ
    0.63
     하고
    0.63
    র্পণ
    0.62
    полне
    0.61
     structure
    0.60
    POSITIVE LOGITS
     originated
    2.11
     origins
    2.01
     roots
    1.98
    origins
    1.80
     originates
    1.80
    起源
    1.71
     origin
    1.68
    origin
    1.68
     began
    1.67
     started
    1.59
    Act Density 0.267%

    No Known Activations