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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    itto
    -0.08
    mass
    -0.07
    ubber
    -0.07
    επ
    -0.07
    finished
    -0.06
    Ingredient
    -0.06
    ardash
    -0.06
     tensions
    -0.06
    원의
    -0.06
    .original
    -0.06
    POSITIVE LOGITS
     podem
    0.06
     konum
    0.06
     baj
    0.06
    =logging
    0.06
    (exp
    0.06
     të
    0.06
     kredi
    0.06
     Columbus
    0.06
     code
    0.06
    .PO
    0.06
    Act Density 0.000%

    No Known Activations