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

    Neuronpedia

    INDEX
    Explanations

    distribution network

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meinem
    -0.07
     meinen
    -0.07
    주는
    -0.06
    �
    -0.06
    '))↵
    -0.06
    alar
    -0.06
     tro
    -0.06
    istros
    -0.06
    …↵
    -0.06
     svensk
    -0.06
    POSITIVE LOGITS
    .intersection
    0.07
     Horror
    0.07
    =model
    0.07
    voor
    0.06
    іль
    0.06
    Codes
    0.06
     Gerry
    0.06
    =`
    0.06
    (torch
    0.06
    .dataset
    0.06
    Act Density 0.040%

    No Known Activations