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

    Neuronpedia

    INDEX
    Explanations

    request for threat

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ጤ
    0.46
     Typography
    0.46
     یورو
    0.44
     bebé
    0.43
    入院
    0.43
     linguaggio
    0.42
     நாட்டு
    0.42
    血压
    0.42
     Tension
    0.42
    躯
    0.42
    POSITIVE LOGITS
     lessen
    0.47
     陳
    0.46
    ន៍
    0.45
     magicians
    0.43
     kn
    0.43
    ьо
    0.43
     throng
    0.42
     roc
    0.42
     hand
    0.42
    ерт
    0.42
    Act Density 0.003%

    No Known Activations