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

    Neuronpedia

    INDEX
    Explanations

    product review

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     قابل
    0.41
     මො
    0.41
    紀錄
    0.41
    mAvailable
    0.40
    纪录
    0.40
    Statements
    0.39
    学習
    0.39
    isyen
    0.39
     लर्निंग
    0.39
    mère
    0.38
    POSITIVE LOGITS
     review
    1.09
     reviews
    1.01
    review
    1.00
     reviewers
    0.89
     Review
    0.88
     REVIEW
    0.87
     reviewing
    0.87
    reviews
    0.86
    Review
    0.85
     обзор
    0.84
    Act Density 0.026%

    No Known Activations