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

    Neuronpedia

    INDEX
    Explanations

    td

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     governo
    -0.07
     andre
    -0.07
    407
    -0.06
    复
    -0.06
    letics
    -0.06
     Gover
    -0.06
    검
    -0.06
     whisper
    -0.06
    (server
    -0.06
    appear
    -0.06
    POSITIVE LOGITS
    .SuppressLint
    0.07
    oad
    0.07
    uant
    0.06
     слишком
    0.06
    bett
    0.06
     Sections
    0.06
     tmp
    0.06
     Vand
    0.06
    izzes
    0.06
    FIG
    0.06
    Act Density 0.004%

    No Known Activations