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

    Neuronpedia

    INDEX
    Explanations

    bet

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    SimpleName
    -0.07
    ustralia
    -0.07
     JV
    -0.06
     Gingrich
    -0.06
    PAIR
    -0.06
    แผน
    -0.06
    ушка
    -0.06
    peaker
    -0.06
     Palmer
    -0.06
    incl
    -0.06
    POSITIVE LOGITS
     Number
    0.08
     addTo
    0.07
     Georg
    0.06
     Item
    0.06
    -controls
    0.06
     Contacts
    0.06
     іде
    0.06
     Date
    0.06
    열
    0.06
    ятся
    0.06
    Act Density 0.009%

    No Known Activations