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

    Neuronpedia

    INDEX
    Explanations

    Code array specifications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    石
    -0.08
     estrateg
    -0.08
    护理
    -0.08
     Hostel
    -0.08
    交通
    -0.07
     sest
    -0.07
     السف
    -0.07
    polis
    -0.07
     láp
    -0.07
     accelerator
    -0.07
    POSITIVE LOGITS
    yes
    0.09
    enk
    0.08
     û
    0.08
    rek
    0.08
    ean
    0.08
    094
    0.08
    elta
    0.08
    0.07
    esto
    0.07
     Cambodia
    0.07
    Act Density 0.001%
    No Known Activations