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

    Neuronpedia

    INDEX
    Explanations

    numbers like 8, 5, and billion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gespr
    0.43
    媾
    0.38
     Edited
    0.37
    ご購入
    0.37
     જન્મદિવસ
    0.36
    出来ない
    0.36
     Fitness
    0.35
     gymnastics
    0.35
     visibly
    0.35
    健身
    0.34
    POSITIVE LOGITS
     TVs
    0.48
     телеви
    0.47
     PC
    0.43
     chave
    0.43
     تلویزی
    0.41
    key
    0.41
     Schlüssel
    0.40
     TV
    0.39
    TNT
    0.39
    テレビ
    0.39
    Act Density 0.003%

    No Known Activations