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

    Neuronpedia

    INDEX
    Explanations

    SD-WAN

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.59
    ５
    0.55
     electroly
    0.55
     electrification
    0.55
    テ
    0.54
    5
    0.53
     rozwiąz
    0.52
     envoyer
    0.52
     sirve
    0.50
    ますが
    0.50
    POSITIVE LOGITS
    u
    0.80
     (
    0.62
    ın
    0.61
    un
    0.56
    را
    0.56
    in
    0.55
    జె
    0.54
    ه
    0.54
    у
    0.53
    ö
    0.51
    Act Density 0.001%

    No Known Activations