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

    Neuronpedia

    INDEX
    Explanations

    pack quantities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     discredited
    0.42
    ීමට
    0.40
     అభివృద్ధి
    0.39
     incompet
    0.39
     سپورټ
    0.39
    積極的に
    0.39
    ाया
    0.39
     ignorant
    0.38
     intolerable
    0.38
     desarrollada
    0.37
    POSITIVE LOGITS
     pack
    0.83
     Pack
    0.79
    Pack
    0.73
    pack
    0.68
     packs
    0.65
     упаков
    0.65
     package
    0.61
     paquete
    0.60
     पैक
    0.59
     PACK
    0.59
    Act Density 0.036%

    No Known Activations