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

    Neuronpedia

    INDEX
    Explanations

    spirit

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     asn
    -0.07
    	Return
    -0.07
    (@(
    -0.07
    (cljs
    -0.07
     cheek
    -0.07
    .nb
    -0.07
     مدى
    -0.06
    וכח
    -0.06
     ―
    -0.06
    ("%.
    -0.06
    POSITIVE LOGITS
    jin
    0.08
    solid
    0.08
    .restaurant
    0.08
     Spirit
    0.08
     Production
    0.08
    Gas
    0.08
    𝘶
    0.07
    灵
    0.07
    neutral
    0.07
    lessness
    0.07
    Act Density 0.013%

    No Known Activations