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

    Neuronpedia

    INDEX
    Explanations

    code related context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ором
    -0.08
    есь
    -0.07
    UEST
    -0.07
    ленных
    -0.07
    ažd
    -0.07
     compute
    -0.07
    ział
    -0.06
     dansk
    -0.06
    OTTOM
    -0.06
    OUS
    -0.06
    POSITIVE LOGITS
    TableView
    0.06
     авг
    0.06
    gold
    0.06
     masc
    0.06
    /random
    0.06
     přes
    0.06
    Trap
    0.06
    .tail
    0.06
    DOWNLOAD
    0.06
     easy
    0.05
    Act Density 1.151%

    No Known Activations