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

    Neuronpedia

    INDEX
    Explanations

    entity recognition

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மட்டுமே
    0.39
     Terbaik
    0.39
     cereals
    0.38
     souhaite
    0.38
    Wiki
    0.37
     votre
    0.37
     uit
    0.37
     സര്‍
    0.37
     حتى
    0.36
     রাখবে
    0.36
    POSITIVE LOGITS
     inasmuch
    0.51
    imeric
    0.44
    多种
    0.42
     firstly
    0.42
     INCRE
    0.41
    INCRE
    0.41
     cargas
    0.40
    各种
    0.39
     titleImageUrl
    0.39
    urgical
    0.39
    Act Density 0.003%

    No Known Activations