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

    Neuronpedia

    INDEX
    Explanations

    Code/API/Database text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arsers
    -0.06
     Challenge
    -0.06
     chatt
    -0.06
    ulist
    -0.06
    wishlist
    -0.06
    _SE
    -0.06
     ذکر
    -0.06
     села
    -0.06
     Flour
    -0.06
    .--
    -0.06
    POSITIVE LOGITS
    عب
    0.07
    -us
    0.06
    .box
    0.06
    (states
    0.06
     ${(
    0.06
    	category
    0.06
     普通
    0.06
     específ
    0.06
     하나
    0.06
     dubbed
    0.06
    Act Density 0.000%

    No Known Activations