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

    Neuronpedia

    INDEX
    Explanations

    safety, options, implications, padding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    昅
    0.41
    䏲
    0.40
    rements
    0.40
    规律
    0.38
    ահ
    0.37
    carriers
    0.36
    rien
    0.36
    bugs
    0.36
    uchs
    0.35
     تھیں
    0.35
    POSITIVE LOGITS
     poster
    0.42
     Artikel
    0.40
    增加了
    0.40
     sensitivity
    0.40
     revest
    0.40
     pariet
    0.38
    цин
    0.38
    Resolve
    0.38
     collagen
    0.38
     пор
    0.38
    Act Density 0.000%

    No Known Activations