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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Originally
    0.50
    んでいます
    0.48
    Originally
    0.47
     हैं
    0.47
    曾
    0.44
     เคย
    0.43
     ursprünglich
    0.42
     당시
    0.41
     है
    0.41
     являются
    0.41
    POSITIVE LOGITS
     seemed
    0.52
     grinned
    0.49
     smiled
    0.47
     chuckled
    0.47
     echoed
    0.46
     laughed
    0.42
     reminded
    0.42
     nodded
    0.42
     explained
    0.42
     sighed
    0.41
    Act Density 0.209%

    No Known Activations