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

    Neuronpedia

    INDEX
    Explanations

    =$(

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    忍
    -0.07
    	to
    -0.07
    .INT
    -0.06
     будів
    -0.06
     Περι
    -0.06
    ところ
    -0.06
     치
    -0.06
     Tricks
    -0.06
    PUR
    -0.06
    戴
    -0.06
    POSITIVE LOGITS
    =$(
    0.09
     leftover
    0.07
    varchar
    0.07
    chrono
    0.06
    .');
    0.06
    except
    0.06
     Dion
    0.06
    667
    0.06
    <head
    0.06
    웅
    0.05
    Act Density 0.002%

    No Known Activations