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

    Neuronpedia

    INDEX
    Explanations

    sentence endings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.80
     day
    0.71
     etc
    0.70
     trough
    0.70
     whole
    0.67
     vaste
    0.66
     same
    0.64
     name
    0.64
     case
    0.64
     hive
    0.64
    POSITIVE LOGITS
    彼は
    0.95
     він
    0.92
     उसने
    0.91
     그는
    0.86
     afirmou
    0.83
     તેણે
    0.81
     उन्‍होंने
    0.81
    他在
    0.80
     egli
    0.78
     യുവാ
    0.78
    Act Density 0.006%

    No Known Activations