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

    Neuronpedia

    INDEX
    Explanations

    Final answer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     […]
    0.37
    യാണ്
    0.36
    <start_of_image>
    0.36
     utility
    0.34
     travels
    0.34
    ٍ
    0.34
    大切
    0.33
    rentices
    0.33
     crashes
    0.33
     capping
    0.33
    POSITIVE LOGITS
    兩種
    0.43
     Sufficient
    0.39
    itton
    0.38
     Formerly
    0.37
     Literally
    0.37
    alte
    0.37
     രണ്ട്
    0.37
     Taken
    0.36
     flavonoids
    0.36
    relaxation
    0.36
    Act Density 0.038%

    No Known Activations