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

    Neuronpedia

    INDEX
    Explanations

    Text HOME to 741741

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    戤
    0.43
    弭
    0.43
    }$,
    0.40
    時候
    0.40
     AM
    0.38
    ड्स
    0.38
    zá
    0.37
     delectable
    0.37
    点了
    0.37
    幻
    0.37
    POSITIVE LOGITS
     문자
    0.44
    tj
    0.35
    混乱
    0.35
     inmedi
    0.35
    iniai
    0.35
    ても
    0.34
     Pubmed
    0.34
    mathrm
    0.34
    ದ್ದರಿಂದ
    0.34
     वेरिफिकेशन
    0.34
    Act Density 0.078%

    No Known Activations