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

    Neuronpedia

    INDEX
    Explanations

    .id

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sid
    -0.07
    arp
    -0.06
    pair
    -0.06
     memo
    -0.06
     lanç
    -0.06
     filme
    -0.06
     migrant
    -0.06
     Ride
    -0.06
     FAA
    -0.06
    ρώ
    -0.06
    POSITIVE LOGITS
     give
    0.07
     barang
    0.07
    ажд
    0.07
    Shopping
    0.07
    RARY
    0.06
    üc
    0.06
     Bah
    0.06
     Wish
    0.06
     Sky
    0.06
     Dě
    0.06
    Act Density 0.000%

    No Known Activations