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

    Neuronpedia

    INDEX
    Explanations

    the final answer is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    クセ
    0.71
     Lleg
    0.69
     nearby
    0.68
     representation
    0.67
    мир
    0.67
    𝑚
    0.66
     branca
    0.66
    千葉
    0.65
     några
    0.65
     যেতে
    0.64
    POSITIVE LOGITS
    倡
    0.75
    ത്തിന്റെയും
    0.75
    reporter
    0.73
    Printing
    0.73
    🏽
    0.72
    gameObject
    0.70
     sensibilities
    0.70
    abilität
    0.69
     отече
    0.69
    Fundamentals
    0.69
    Act Density 0.011%

    No Known Activations