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

    Neuronpedia

    INDEX
    Explanations

    K-Means, service, shuttle

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ماين
    0.51
     Fortnite
    0.50
     Resolved
    0.41
    Amt
    0.41
    Biden
    0.40
    Resolved
    0.40
     bipartisan
    0.40
     enjeux
    0.40
     Kardashians
    0.40
    chyné
    0.39
    POSITIVE LOGITS
    initis
    0.48
    ilingual
    0.45
    服務
    0.45
    ifice
    0.44
    –
    0.44
    anje
    0.44
     secretariat
    0.43
     photocopying
    0.43
    iding
    0.42
    iciones
    0.42
    Act Density 0.004%

    No Known Activations