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

    Neuronpedia

    INDEX
    Explanations

    discovery, deployment, explanation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ጥላ
    0.50
    Кли
    0.48
    リスト
    0.45
    êng
    0.44
     likeness
    0.43
     tranquility
    0.43
    RectangleShape
    0.43
     subsequence
    0.42
    ைய
    0.42
    ParentObject
    0.42
    POSITIVE LOGITS
    beta
    0.52
    /(
    0.50
    ّد
    0.45
     beta
    0.43
     betas
    0.43
     neem
    0.43
    得上
    0.43
    zend
    0.42
     Maya
    0.42
     validators
    0.42
    Act Density 0.002%

    No Known Activations