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

    Neuronpedia

    INDEX
    Explanations

    Grouping in experiments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pired
    -0.08
    -season
    -0.07
     Turbo
    -0.07
     could
    -0.06
     muscles
    -0.06
    639
    -0.06
     households
    -0.06
     Asian
    -0.06
     sunk
    -0.06
    histor
    -0.06
    POSITIVE LOGITS
    カテゴリ
    0.07
    ━━━━━━━━
    0.07
     Sın
    0.06
     سبب
    0.06
    ;">
↵
    0.06
    (Border
    0.06
    _WP
    0.06
     आवश
    0.06
    _mv
    0.06
    liğinde
    0.06
    Act Density 0.060%

    No Known Activations