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

    Neuronpedia

    INDEX
    Explanations

    solving math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sheet
    -0.07
    	world
    -0.07
    evento
    -0.07
    Finite
    -0.07
     MEMORY
    -0.07
    $sub
    -0.07
     environmental
    -0.07
     west
    -0.06
    naire
    -0.06
     تشکیل
    -0.06
    POSITIVE LOGITS
     वजह
    0.07
     انواع
    0.06
    こちら
    0.06
    aepernick
    0.06
    の一
    0.06
    .userName
    0.06
     등의
    0.06
     Guantanamo
    0.06
     الأك
    0.06
    чины
    0.06
    Act Density 0.014%

    No Known Activations