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

    Neuronpedia

    INDEX
    Explanations

    the [noun]

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     a
    0.88
     ஒரு
    0.88
     ഒരു
    0.86
    的一种
    0.84
    ционный
    0.81
     ஓர்
    0.80
     an
    0.77
     one
    0.77
     một
    0.77
     полное
    0.75
    POSITIVE LOGITS
     caveats
    0.87
     failures
    0.79
     counties
    0.77
     objections
    0.75
     ingredients
    0.74
     takers
    0.73
     enquiries
    0.73
     things
    0.72
     pieces
    0.72
     materials
    0.72
    Act Density 0.254%

    No Known Activations