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

    Neuronpedia

    INDEX
    Explanations

    ON or OFF switch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     effettu
    0.48
    <ul>
    0.46
    də
    0.46
    d
    0.45
     प्रखंड
    0.45
    Demand
    0.44
     Demand
    0.42
    だが
    0.42
    EV
    0.41
    dur
    0.41
    POSITIVE LOGITS
     vision
    0.44
     සො
    0.43
     मिळेल
    0.42
     fast
    0.42
    resos
    0.41
     Commonwealth
    0.41
    とき
    0.41
    erals
    0.41
    ીર
    0.40
     search
    0.39
    Act Density 0.001%

    No Known Activations