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

    Neuronpedia

    INDEX
    Explanations

    comparisons and statistics

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    京都
    -0.06
    excerpt
    -0.06
    ovah
    -0.06
    ладу
    -0.06
     Buddhism
    -0.06
     camper
    -0.06
    �
    -0.06
    キング
    -0.05
     Bootstrap
    -0.05
     levy
    -0.05
    POSITIVE LOGITS
    里面
    0.07
     mileage
    0.07
    talya
    0.07
    ijk
    0.06
    olon
    0.06
    senal
    0.06
    .anim
    0.06
    (sheet
    0.06
    岗
    0.06
     "-"↵
    0.06
    Act Density 0.280%

    No Known Activations