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

    Neuronpedia

    INDEX
    Explanations

    communication channels

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    番号
    -0.07
     Epstein
    -0.07
    лять
    -0.06
    itu
    -0.06
    Ж
    -0.06
     smile
    -0.06
     tabBar
    -0.06
    まず
    -0.06
     CO
    -0.06
    荣
    -0.06
    POSITIVE LOGITS
     RequestContext
    0.07
     빈
    0.06
    .bean
    0.06
    _REC
    0.06
    。不
    0.06
    ederland
    0.06
     chats
    0.06
     Más
    0.06
     graf
    0.06
     httpResponse
    0.06
    Act Density 0.029%

    No Known Activations