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

    Neuronpedia

    INDEX
    Explanations

    Indonesian text

    oai_token-act-pair · gemini-2.0-flash

    Code and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     للاسماء
    -0.62
    ISupport
    -0.62
     الحره
    -0.57
     оригіналу
    -0.55
    asjoner
    -0.54
    رشف
    -0.52
     propOrder
    -0.49
     opérés
    -0.48
     goa
    -0.47
     rechange
    -0.46
    POSITIVE LOGITS
    /**
    0.68
    ✫
    0.56
     ProtoMessage
    0.56
    GOTREF
    0.55
    vocable
    0.55
    bello
    0.54
     memimpin
    0.53
     pagare
    0.52
     memeriksa
    0.52
     membunuh
    0.52
    Act Density 0.325%

    No Known Activations