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

    Neuronpedia

    INDEX
    Explanations

    Foreign words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Graphics
    -0.08
    _ratio
    -0.07
    -middle
    -0.07
    .setForeground
    -0.06
    蛀
    -0.06
     rob
    -0.06
    쫓
    -0.06
     Vlad
    -0.06
    CustomAttributes
    -0.06
    Road
    -0.06
    POSITIVE LOGITS
    問題
    0.07
    King
    0.07
    火星
    0.07
    ense
    0.06
     כי
    0.06
    兴趣
    0.06
     sou
    0.06
    _mgmt
    0.06
    -agent
    0.06
    	errors
    0.06
    Act Density 0.123%

    No Known Activations