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

    Neuronpedia

    INDEX
    Explanations

    past tense verbs ending in -ed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     você
    0.67
     veya
    0.67
     yoki
    0.58
    หรือ
    0.55
    基本的に
    0.54
     you
    0.53
     altid
    0.53
    或
    0.53
    you
    0.52
     hoặc
    0.52
    POSITIVE LOGITS
     gleaming
    0.72
     plump
    0.65
    缓缓
    0.65
    只见
    0.63
     comenzaron
    0.61
    轻轻
    0.61
    丁寧に
    0.61
     hesit
    0.59
     delicately
    0.58
    熟悉的
    0.58
    Act Density 0.026%

    No Known Activations