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

    Neuronpedia

    INDEX
    Explanations

    javascript file inclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     entschied
    0.48
    చ్చే
    0.42
    ર્ક
    0.41
    Panoramic
    0.39
     jun
    0.37
     যাদ
    0.37
    ensemble
    0.35
     estudo
    0.35
     लीवर
    0.35
    गत
    0.35
    POSITIVE LOGITS
    "></
    0.89
     ></
    0.75
    ></
    0.66
    '></
    0.60
    }></
    0.59
    "</
    0.50
     defer
    0.48
    .</
    0.45
     "</
    0.43
     crossorigin
    0.43
    Act Density 0.004%

    No Known Activations